SlideShare a Scribd company logo
1 of 39
Download to read offline
Deniz Beker

Engineer, Preferred Networks



March 2021

Introduction to 3D Computer Vision:
Applications & Challenges
● What is 3D Computer Vision?
● What is Differentiable Rendering (DR)?
● How Differentiable Rendering Works?
● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection”
● Other examples
● Open Discussion
Agenda
Education:
• Isik University, Istanbul, BSc. Electronics Engineering, 2011
• Yeditepe University, Istanbul, MSc. Electronics Engineering, 2014
Experience:
• Huawei R&D Center, Istanbul, SW Engineer, 2012-2014
• Ayonix Inc, Tokyo, SW Engineer, 2014-2015
• TeraRecon Inc, Tokyo, SW Engineer, 2015-2017
• Preferred Networks, Tokyo, Engineer, 2018 -
• Preferred Networks, Tokyo, Engineer / Engineering Manager, 2019-2021
Freelance:
• Managed & Consulted several projects based on 3D Computer Vision and Cloud Gaming
Introduction - Deniz Beker
What is 3D Computer Vision?
Sequential
Data
Text
1-D Data
Image
2-D Data
What is 3D Computer Vision?
Multi-View 3D Object Detection Network For Autonomous Driving,
Chen et. al., 2017
3D Perception 3D Object Detection
Shape Segmentation & Classification
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, Qi et al. 2017 Convolutional Occupancy Networks, Peng et al, 2020
Shape Completion
&
Denoising
And many other applications...
● What is 3D Computer Vision?
● What is Differentiable Rendering (DR)?
● How Differentiable Rendering Works?
● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection”
● Other examples
● Open Discussion
Agenda
Supervised Deep Learning Pipeline
1
0
Input Data
Forward Pass

Calculate Error
Labels /
Supervision
● Penalize each neuron w.r.t. their
contribution to error
● Reiterate
Supervision Challenges in 3D Computer Vision
● It is not easy to label 3D data accurately
(where to click, how to label, it is an open HCI problem)
● Sometimes, it is impossible to generate 3D labels
(i.e. light directions in an image in the wild)
● It is costly to collect 3D data
(Most likely need to equip LIDAR-like equipment for precise data collection)
Self-Supervised Solution: Differentiable Rendering
● Projective Geometry Aware
Dimensionality Reduction (3D -> 2D)
● Allowing usage of 2D input images as
self-supervision to predict 3D parameters
● Estimating the 3D world parameters only
from 2D observations
● What is 3D Computer Vision?
● What is Differentiable Rendering (DR)?
● How Differentiable Rendering Works?
● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection”
● Other examples
● Open Discussion
Agenda
3D Shape Representations Types
Point Cloud Mesh Voxel Implicit Function
RGB Rendering
(For Reference)
Source: Semantic and instance segmentation based on 3D point cloud scenes: RandLA-Net and 3D-BoNet
Explicit Representations
 Implicit Representation

Rendering: Rasterization in OpenGL pipeline
The aim is to project 3D geometry & scene
information to a 2D plane
● Project each triangle to screen space
● Order each triangle based on depth and
determine which one is visible
● Mark each pixels that lie inside each visible
triangle
● Apply texture to those pixels for color
● Post process (optional)
○ Light
○ Reflection & Refraction
○ Shadow
Source:
https://developer.tizen.org/ko/forums/native-application-development/what-rasterisation-opengl-graphic-pipeline
Rendering: Ray Tracing
The aim is to bind each hypothetical line
segments from a pixel to a light source
● For each pixel, shoot a ray and check if it hits
to a light or a surface
● If it hits to a surface, calculate possible
refractions & reflections to generate N more
rays
● Follow those rays and repeat the process
until a ray hits to a light
● If any ray hits to a light, calculate the color
by combining light intensity, light color,
material refraction & reflection parameters
● Combine the impact of multiple rays if they
affect same pixel
Source: https://en.wikipedia.org/wiki/Ray_tracing_(graphics)
Analytical Derivative of Mesh Rasterization
Mesh Vertices Vp
Vertices @ Screen Space
Order & Choose Visible Triangles
Assign Color To A Pixel Through Texture
Post Process For Light etc.
Not Differentiable Due Discrete Nature
Differentiable By Default
Differentiable By Default
Differentiable By Default
Pixel Color Vc
Rasterize (Digitize)
Differentiable By Default
Differentiating Mesh Rasterization
There are two main problems to solve to differentiate a rendering:
● How to create gradients / backpropagate for object (foreground) pixels?
● How to create gradients / backpropagate for non-object (background pixels)?
There are two mainstream approaches to handle this problem:
● Approximating Gradients (Backward Pass)
● Approximating Rasterization (Forward Pass)
Approximating Gradients
Opendr: An approximate differentiable renderer, M. M. Loper and M. J. Black. ECCV, 2014.
Neural 3d mesh renderer, H. Kato, Y. Ushiku, and T. Harada. CVPR, 2018.
● Find the visible triangle per pixel pi
● Find the pi’s projection Pi on 3D
triangle
● Using inverse barycentric coordinate
calculation, find the weights of
triangle’s vertices Vx at point Pi
● Assign the weighted value of gradient
of Pi to each Vx
● Propagate gradients for background
pixels in screen space from
neighbouring pixels (OpenDR) or same
column / row (NMR)
Approximating Gradients
Opendr: An approximate differentiable renderer, M. M. Loper and M. J. Black. ECCV, 2014.
Neural 3d mesh renderer, H. Kato, Y. Ushiku, and T. Harada. CVPR, 2018.
Advantages:
● Provides “useful” gradients
● Any professional rasterizer can be
used for forward pass
Disadvantages:
● Handcrafting gradients are hard,
complex and time consuming
● Point pi will not propagate any
gradients
● Fails if accurate gradients are required
Approximating Mesh Rasterization
Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
S. Liu, T. Li, W. Chen, H. Li
Advantages:
● Automatic & Accurate gradient calculation
● Each pixel is covered for gradient
Disadvantages:
● Blurry output
● Computationally expensive
Differentiating point cloud rendering
There is no rasterization => Theoretically all pipeline is differentiable
However, there is still a problem due discrete nature of the images
What will happen if multiple points are projected to the same pixel?
What will be the final color? How to backpropagate?
Learning Efficient Point Cloud Generation for Dense
3D Object Reconstruction
Lin et al.
Differentiating point cloud rendering
Learning Efficient Point Cloud Generation for Dense
3D Object Reconstruction
Lin et al.
- Increase spatial dimensions to ensure unique projection
- Apply max / mean pooling operation
- Add a pseudo-size to each point
- Apply weighted / probabilistic aggregation for pixel color
End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
Li et al.
Differentiating voxel rendering
Ray marching is differentiable by nature!
Differentiable Ray Marching can be
implemented as a cumulative sum of voxel
occupancy values across a ray
However, it has O(n^3) memory complexity
Neural Volumes: Learning Dynamic Renderable Volumes From Images, Lombardi et al.
Differentiating Ray Tracing
● Functions are differentiable by nature
● Discontinuity exists at object edges and
due occlusions
● Approximation / Sampling strategies to
overcome this problem
Neural Rendering
● Rendering as NN layers
● Requires learning
● Easier to implement vs previous ones
● Geometry consistency is not guaranteed
Deferred Neural Rendering: Image Synthesis using Neural Textures, Theis et al., 2019
Shapes as Implicit Functions
x
y
Consider the aim is to represent this circle in 2D
Mesh / Point Cloud: Sample N points on circle
(N x 2 parameters to represent)
Voxel: Cubify / Discretize to M bins
(M x M parameters to represent)
Implicit Fn: Define the function & Evaluate for (N) or (M x M) points
(3 parameters to represent, a, b, c)
f(x1
, y1
)
f(x2
, y2
)
f(x3
, y3
)
.
.
.
f(xN
, yN
)
f(x1
, y1
)
f(x2
, y2
)
f(x3
, y3
)
..
.
f(xM
, yM
)
Neural Implicit Scene Representations
Let’s increase the complexity and represent the following 3D object as an implicit
function. Not possible to handcraft the functions to represent the shape!
Scene Representation Networks, Sitzmann et al. 2019
Why Implicit Scene Representations Are Important?
● Infinite resolution for spatial dimensions / No more OOM due large voxel sizes!
● Defines scene as a continuous function (all explicit repr. are discrete)
● Allows defining level of detail during inference, no need to change network & retrain
● Can embed different meta information, along with occupancy
● Possibility to remove expensive 3D CNNs to process the volume
● What is 3D Computer Vision?
● What is Differentiable Rendering (DR)?
● How Differentiable Rendering works?
● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection”
● Other examples
● Open Discussion
Agenda
Applications:
Self-Supervision for 3D Object Detection
Monocular Differentiable Rendering for Self-Supervised 3D Object Detection,
D.Beker, H.Kato, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, A. Gaidon, ECCV 2020
Purpose:
Given monocular RGB image (and camera calibrations)
Predict 3D dimension, texture, rotation and location of the objects in metric scale
Through self-supervision, generate 3D annotations automatically
Applications:
Self-Supervision for 3D Object Detection
Optimization Iterations
● What is 3D Computer Vision?
● What is Differentiable Rendering (DR)?
● How Differentiable Rendering works?
● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection”
● Other examples
● Open Discussion
Agenda
Other Applications of Differentiable Rendering
Example - NeRF
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis,
Mildenhall et al. ECCV Oral 2020
These 3D reconstructions are produced
only by using 2D observations.
Example - D-NeRF (a.k.a. Nerfies)
D-NeRF: Neural Radiance Fields for Dynamic Scenes
Pumarola et al. 2020
Example - DeepSDF
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation,
Park et. al. 2019
Shape as Signed Distance Function
Example - Convolutional Occupancy Networks
Convolutional Occupancy Networks, Peng et. al. 2020 Occupancy prediction at a 3D point,
conditional on input features
Example - SIREN
Implicit Neural Representations with Periodic Activation Functions,
Sitzmann et. al, NeurIPS 2020 (Oral)
Replacing the activation layers with
periodic functions improves the
model’s capacity with same number of
parameters
There are more algorithms and applications
For other algorithms, please check our survey paper
Differentiable Rendering: A Survey, H. Kato, D. Beker, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, A. Gaidon
Open Discussion
Introduction to 3D Computer Vision and Differentiable Rendering

More Related Content

What's hot

【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptxARISE analytics
 
Real-Time Semantic Stereo Matching
Real-Time Semantic Stereo MatchingReal-Time Semantic Stereo Matching
Real-Time Semantic Stereo Matchingharmonylab
 
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...Deep Learning JP
 
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...Deep Learning JP
 
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"Deep Learning JP
 
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...Deep Learning JP
 
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)Masaya Kaneko
 
【CVPR 2019】Do Better ImageNet Models Transfer Better?
【CVPR 2019】Do Better ImageNet Models Transfer Better?【CVPR 2019】Do Better ImageNet Models Transfer Better?
【CVPR 2019】Do Better ImageNet Models Transfer Better?cvpaper. challenge
 
30th コンピュータビジョン勉強会@関東 DynamicFusion
30th コンピュータビジョン勉強会@関東 DynamicFusion30th コンピュータビジョン勉強会@関東 DynamicFusion
30th コンピュータビジョン勉強会@関東 DynamicFusionHiroki Mizuno
 
(文献紹介)Depth Completionの最新動向
(文献紹介)Depth Completionの最新動向(文献紹介)Depth Completionの最新動向
(文献紹介)Depth Completionの最新動向Morpho, Inc.
 
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)Yamato OKAMOTO
 
SfM Learner系単眼深度推定手法について
SfM Learner系単眼深度推定手法についてSfM Learner系単眼深度推定手法について
SfM Learner系単眼深度推定手法についてRyutaro Yamauchi
 
Neural scene representation and rendering の解説(第3回3D勉強会@関東)
Neural scene representation and rendering の解説(第3回3D勉強会@関東)Neural scene representation and rendering の解説(第3回3D勉強会@関東)
Neural scene representation and rendering の解説(第3回3D勉強会@関東)Masaya Kaneko
 
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得Masayuki Tanaka
 
ガイデットフィルタとその周辺
ガイデットフィルタとその周辺ガイデットフィルタとその周辺
ガイデットフィルタとその周辺Norishige Fukushima
 
三次元点群を取り扱うニューラルネットワークのサーベイ
三次元点群を取り扱うニューラルネットワークのサーベイ三次元点群を取り扱うニューラルネットワークのサーベイ
三次元点群を取り扱うニューラルネットワークのサーベイNaoya Chiba
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative ModelsDeep Learning JP
 
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View SynthesisKento Doi
 
SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII
 

What's hot (20)

【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
【論文読み会】BEiT_BERT Pre-Training of Image Transformers.pptx
 
Real-Time Semantic Stereo Matching
Real-Time Semantic Stereo MatchingReal-Time Semantic Stereo Matching
Real-Time Semantic Stereo Matching
 
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...
【DL輪読会】Visual Classification via Description from Large Language Models (ICLR...
 
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
 
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
 
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...
[DL輪読会]A Higher-Dimensional Representation for Topologically Varying Neural R...
 
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)
Visual SLAM: Why Bundle Adjust?の解説(第4回3D勉強会@関東)
 
【CVPR 2019】Do Better ImageNet Models Transfer Better?
【CVPR 2019】Do Better ImageNet Models Transfer Better?【CVPR 2019】Do Better ImageNet Models Transfer Better?
【CVPR 2019】Do Better ImageNet Models Transfer Better?
 
30th コンピュータビジョン勉強会@関東 DynamicFusion
30th コンピュータビジョン勉強会@関東 DynamicFusion30th コンピュータビジョン勉強会@関東 DynamicFusion
30th コンピュータビジョン勉強会@関東 DynamicFusion
 
(文献紹介)Depth Completionの最新動向
(文献紹介)Depth Completionの最新動向(文献紹介)Depth Completionの最新動向
(文献紹介)Depth Completionの最新動向
 
実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE実装レベルで学ぶVQVAE
実装レベルで学ぶVQVAE
 
Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)Domain Adaptation 発展と動向まとめ(サーベイ資料)
Domain Adaptation 発展と動向まとめ(サーベイ資料)
 
SfM Learner系単眼深度推定手法について
SfM Learner系単眼深度推定手法についてSfM Learner系単眼深度推定手法について
SfM Learner系単眼深度推定手法について
 
Neural scene representation and rendering の解説(第3回3D勉強会@関東)
Neural scene representation and rendering の解説(第3回3D勉強会@関東)Neural scene representation and rendering の解説(第3回3D勉強会@関東)
Neural scene representation and rendering の解説(第3回3D勉強会@関東)
 
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
遠赤外線カメラと可視カメラを利用した悪条件下における画像取得
 
ガイデットフィルタとその周辺
ガイデットフィルタとその周辺ガイデットフィルタとその周辺
ガイデットフィルタとその周辺
 
三次元点群を取り扱うニューラルネットワークのサーベイ
三次元点群を取り扱うニューラルネットワークのサーベイ三次元点群を取り扱うニューラルネットワークのサーベイ
三次元点群を取り扱うニューラルネットワークのサーベイ
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models
 
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
[解説スライド] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
 
SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向
 

Similar to Introduction to 3D Computer Vision and Differentiable Rendering

Deep learning for 3 d point clouds presentation
Deep learning for 3 d point clouds presentationDeep learning for 3 d point clouds presentation
Deep learning for 3 d point clouds presentationVijaylaxmiNagurkar
 
3-d interpretation from single 2-d image for autonomous driving II
3-d interpretation from single 2-d image for autonomous driving II3-d interpretation from single 2-d image for autonomous driving II
3-d interpretation from single 2-d image for autonomous driving IIYu Huang
 
Summary of survey papers on deep learning method to 3D data
Summary of survey papers on deep learning method to 3D dataSummary of survey papers on deep learning method to 3D data
Summary of survey papers on deep learning method to 3D dataArithmer Inc.
 
3D Image visualization
3D Image visualization3D Image visualization
3D Image visualizationalok ray
 
From Experimentation to Production: The Future of WebGL
From Experimentation to Production: The Future of WebGLFrom Experimentation to Production: The Future of WebGL
From Experimentation to Production: The Future of WebGLFITC
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術CHENHuiMei
 
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Skolkovo Robotics Center
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - Hiroshi Fukui
 
Conception_et_realisation_dun_site_Web_d.pdf
Conception_et_realisation_dun_site_Web_d.pdfConception_et_realisation_dun_site_Web_d.pdf
Conception_et_realisation_dun_site_Web_d.pdfSofianeHassine2
 
Understanding neural radiance fields
Understanding neural radiance fieldsUnderstanding neural radiance fields
Understanding neural radiance fieldsVarun Bhaseen
 
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdfmokamojah
 
Rendering Algorithms.pptx
Rendering Algorithms.pptxRendering Algorithms.pptx
Rendering Algorithms.pptxSherinRappai
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMeetupDataScienceRoma
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human labelKai-Wen Zhao
 
LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)Yu Huang
 

Similar to Introduction to 3D Computer Vision and Differentiable Rendering (20)

Deep learning for 3 d point clouds presentation
Deep learning for 3 d point clouds presentationDeep learning for 3 d point clouds presentation
Deep learning for 3 d point clouds presentation
 
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
 
Deep 3D Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2018
Deep 3D Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2018Deep 3D Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2018
Deep 3D Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2018
 
3-d interpretation from single 2-d image for autonomous driving II
3-d interpretation from single 2-d image for autonomous driving II3-d interpretation from single 2-d image for autonomous driving II
3-d interpretation from single 2-d image for autonomous driving II
 
Summary of survey papers on deep learning method to 3D data
Summary of survey papers on deep learning method to 3D dataSummary of survey papers on deep learning method to 3D data
Summary of survey papers on deep learning method to 3D data
 
3D Image visualization
3D Image visualization3D Image visualization
3D Image visualization
 
From Experimentation to Production: The Future of WebGL
From Experimentation to Production: The Future of WebGLFrom Experimentation to Production: The Future of WebGL
From Experimentation to Production: The Future of WebGL
 
RWDA
RWDARWDA
RWDA
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
lecture_16_jiajun.pdf
lecture_16_jiajun.pdflecture_16_jiajun.pdf
lecture_16_jiajun.pdf
 
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
Conception_et_realisation_dun_site_Web_d.pdf
Conception_et_realisation_dun_site_Web_d.pdfConception_et_realisation_dun_site_Web_d.pdf
Conception_et_realisation_dun_site_Web_d.pdf
 
Understanding neural radiance fields
Understanding neural radiance fieldsUnderstanding neural radiance fields
Understanding neural radiance fields
 
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf10.1109@ICCMC48092.2020.ICCMC-000167.pdf
10.1109@ICCMC48092.2020.ICCMC-000167.pdf
 
Rendering Algorithms.pptx
Rendering Algorithms.pptxRendering Algorithms.pptx
Rendering Algorithms.pptx
 
Mirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image ProcessingMirko Lucchese - Deep Image Processing
Mirko Lucchese - Deep Image Processing
 
Learning visual representation without human label
Learning visual representation without human labelLearning visual representation without human label
Learning visual representation without human label
 
3D 딥러닝 동향
3D 딥러닝 동향3D 딥러닝 동향
3D 딥러닝 동향
 
LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)
 

More from Preferred Networks

PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57Preferred Networks
 
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3Preferred Networks
 
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...Preferred Networks
 
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...Preferred Networks
 
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55Preferred Networks
 
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2Preferred Networks
 
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2Preferred Networks
 
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2Preferred Networks
 
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演Preferred Networks
 
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)Preferred Networks
 
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)Preferred Networks
 
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)Preferred Networks
 
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語るKubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語るPreferred Networks
 
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張Preferred Networks
 
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会Preferred Networks
 
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2Preferred Networks
 
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...Preferred Networks
 
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...Preferred Networks
 
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...Preferred Networks
 
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50Preferred Networks
 

More from Preferred Networks (20)

PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
 
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
 
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
 
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
 
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
 
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
 
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
 
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
 
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
 
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
 
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
 
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
 
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語るKubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
 
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
 
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
 
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
 
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
 
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
 
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
 
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
 

Recently uploaded

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DaySri Ambati
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Manik S Magar
 

Recently uploaded (20)

Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo DayH2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
H2O.ai CEO/Founder: Sri Ambati Keynote at Wells Fargo Day
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdf
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!Anypoint Exchange: It’s Not Just a Repo!
Anypoint Exchange: It’s Not Just a Repo!
 

Introduction to 3D Computer Vision and Differentiable Rendering

  • 1. Deniz Beker
 Engineer, Preferred Networks
 
 March 2021
 Introduction to 3D Computer Vision: Applications & Challenges
  • 2. ● What is 3D Computer Vision? ● What is Differentiable Rendering (DR)? ● How Differentiable Rendering Works? ● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection” ● Other examples ● Open Discussion Agenda
  • 3. Education: • Isik University, Istanbul, BSc. Electronics Engineering, 2011 • Yeditepe University, Istanbul, MSc. Electronics Engineering, 2014 Experience: • Huawei R&D Center, Istanbul, SW Engineer, 2012-2014 • Ayonix Inc, Tokyo, SW Engineer, 2014-2015 • TeraRecon Inc, Tokyo, SW Engineer, 2015-2017 • Preferred Networks, Tokyo, Engineer, 2018 - • Preferred Networks, Tokyo, Engineer / Engineering Manager, 2019-2021 Freelance: • Managed & Consulted several projects based on 3D Computer Vision and Cloud Gaming Introduction - Deniz Beker
  • 4. What is 3D Computer Vision? Sequential Data Text 1-D Data Image 2-D Data
  • 5. What is 3D Computer Vision? Multi-View 3D Object Detection Network For Autonomous Driving, Chen et. al., 2017 3D Perception 3D Object Detection Shape Segmentation & Classification PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation, Qi et al. 2017 Convolutional Occupancy Networks, Peng et al, 2020 Shape Completion & Denoising And many other applications...
  • 6. ● What is 3D Computer Vision? ● What is Differentiable Rendering (DR)? ● How Differentiable Rendering Works? ● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection” ● Other examples ● Open Discussion Agenda
  • 7. Supervised Deep Learning Pipeline 1 0 Input Data Forward Pass
 Calculate Error Labels / Supervision ● Penalize each neuron w.r.t. their contribution to error ● Reiterate
  • 8. Supervision Challenges in 3D Computer Vision ● It is not easy to label 3D data accurately (where to click, how to label, it is an open HCI problem) ● Sometimes, it is impossible to generate 3D labels (i.e. light directions in an image in the wild) ● It is costly to collect 3D data (Most likely need to equip LIDAR-like equipment for precise data collection)
  • 9. Self-Supervised Solution: Differentiable Rendering ● Projective Geometry Aware Dimensionality Reduction (3D -> 2D) ● Allowing usage of 2D input images as self-supervision to predict 3D parameters ● Estimating the 3D world parameters only from 2D observations
  • 10. ● What is 3D Computer Vision? ● What is Differentiable Rendering (DR)? ● How Differentiable Rendering Works? ● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection” ● Other examples ● Open Discussion Agenda
  • 11. 3D Shape Representations Types Point Cloud Mesh Voxel Implicit Function RGB Rendering (For Reference) Source: Semantic and instance segmentation based on 3D point cloud scenes: RandLA-Net and 3D-BoNet Explicit Representations
 Implicit Representation

  • 12. Rendering: Rasterization in OpenGL pipeline The aim is to project 3D geometry & scene information to a 2D plane ● Project each triangle to screen space ● Order each triangle based on depth and determine which one is visible ● Mark each pixels that lie inside each visible triangle ● Apply texture to those pixels for color ● Post process (optional) ○ Light ○ Reflection & Refraction ○ Shadow Source: https://developer.tizen.org/ko/forums/native-application-development/what-rasterisation-opengl-graphic-pipeline
  • 13. Rendering: Ray Tracing The aim is to bind each hypothetical line segments from a pixel to a light source ● For each pixel, shoot a ray and check if it hits to a light or a surface ● If it hits to a surface, calculate possible refractions & reflections to generate N more rays ● Follow those rays and repeat the process until a ray hits to a light ● If any ray hits to a light, calculate the color by combining light intensity, light color, material refraction & reflection parameters ● Combine the impact of multiple rays if they affect same pixel Source: https://en.wikipedia.org/wiki/Ray_tracing_(graphics)
  • 14. Analytical Derivative of Mesh Rasterization Mesh Vertices Vp Vertices @ Screen Space Order & Choose Visible Triangles Assign Color To A Pixel Through Texture Post Process For Light etc. Not Differentiable Due Discrete Nature Differentiable By Default Differentiable By Default Differentiable By Default Pixel Color Vc Rasterize (Digitize) Differentiable By Default
  • 15. Differentiating Mesh Rasterization There are two main problems to solve to differentiate a rendering: ● How to create gradients / backpropagate for object (foreground) pixels? ● How to create gradients / backpropagate for non-object (background pixels)? There are two mainstream approaches to handle this problem: ● Approximating Gradients (Backward Pass) ● Approximating Rasterization (Forward Pass)
  • 16. Approximating Gradients Opendr: An approximate differentiable renderer, M. M. Loper and M. J. Black. ECCV, 2014. Neural 3d mesh renderer, H. Kato, Y. Ushiku, and T. Harada. CVPR, 2018. ● Find the visible triangle per pixel pi ● Find the pi’s projection Pi on 3D triangle ● Using inverse barycentric coordinate calculation, find the weights of triangle’s vertices Vx at point Pi ● Assign the weighted value of gradient of Pi to each Vx ● Propagate gradients for background pixels in screen space from neighbouring pixels (OpenDR) or same column / row (NMR)
  • 17. Approximating Gradients Opendr: An approximate differentiable renderer, M. M. Loper and M. J. Black. ECCV, 2014. Neural 3d mesh renderer, H. Kato, Y. Ushiku, and T. Harada. CVPR, 2018. Advantages: ● Provides “useful” gradients ● Any professional rasterizer can be used for forward pass Disadvantages: ● Handcrafting gradients are hard, complex and time consuming ● Point pi will not propagate any gradients ● Fails if accurate gradients are required
  • 18. Approximating Mesh Rasterization Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning S. Liu, T. Li, W. Chen, H. Li Advantages: ● Automatic & Accurate gradient calculation ● Each pixel is covered for gradient Disadvantages: ● Blurry output ● Computationally expensive
  • 19. Differentiating point cloud rendering There is no rasterization => Theoretically all pipeline is differentiable However, there is still a problem due discrete nature of the images What will happen if multiple points are projected to the same pixel? What will be the final color? How to backpropagate? Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction Lin et al.
  • 20. Differentiating point cloud rendering Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction Lin et al. - Increase spatial dimensions to ensure unique projection - Apply max / mean pooling operation - Add a pseudo-size to each point - Apply weighted / probabilistic aggregation for pixel color End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds Li et al.
  • 21. Differentiating voxel rendering Ray marching is differentiable by nature! Differentiable Ray Marching can be implemented as a cumulative sum of voxel occupancy values across a ray However, it has O(n^3) memory complexity Neural Volumes: Learning Dynamic Renderable Volumes From Images, Lombardi et al.
  • 22. Differentiating Ray Tracing ● Functions are differentiable by nature ● Discontinuity exists at object edges and due occlusions ● Approximation / Sampling strategies to overcome this problem
  • 23. Neural Rendering ● Rendering as NN layers ● Requires learning ● Easier to implement vs previous ones ● Geometry consistency is not guaranteed Deferred Neural Rendering: Image Synthesis using Neural Textures, Theis et al., 2019
  • 24. Shapes as Implicit Functions x y Consider the aim is to represent this circle in 2D Mesh / Point Cloud: Sample N points on circle (N x 2 parameters to represent) Voxel: Cubify / Discretize to M bins (M x M parameters to represent) Implicit Fn: Define the function & Evaluate for (N) or (M x M) points (3 parameters to represent, a, b, c) f(x1 , y1 ) f(x2 , y2 ) f(x3 , y3 ) . . . f(xN , yN ) f(x1 , y1 ) f(x2 , y2 ) f(x3 , y3 ) .. . f(xM , yM )
  • 25. Neural Implicit Scene Representations Let’s increase the complexity and represent the following 3D object as an implicit function. Not possible to handcraft the functions to represent the shape! Scene Representation Networks, Sitzmann et al. 2019
  • 26. Why Implicit Scene Representations Are Important? ● Infinite resolution for spatial dimensions / No more OOM due large voxel sizes! ● Defines scene as a continuous function (all explicit repr. are discrete) ● Allows defining level of detail during inference, no need to change network & retrain ● Can embed different meta information, along with occupancy ● Possibility to remove expensive 3D CNNs to process the volume
  • 27. ● What is 3D Computer Vision? ● What is Differentiable Rendering (DR)? ● How Differentiable Rendering works? ● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection” ● Other examples ● Open Discussion Agenda
  • 28. Applications: Self-Supervision for 3D Object Detection Monocular Differentiable Rendering for Self-Supervised 3D Object Detection, D.Beker, H.Kato, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, A. Gaidon, ECCV 2020 Purpose: Given monocular RGB image (and camera calibrations) Predict 3D dimension, texture, rotation and location of the objects in metric scale Through self-supervision, generate 3D annotations automatically
  • 29. Applications: Self-Supervision for 3D Object Detection Optimization Iterations
  • 30. ● What is 3D Computer Vision? ● What is Differentiable Rendering (DR)? ● How Differentiable Rendering works? ● Application “Monocular Differentiable Rendering for Self-Supervised Object Detection” ● Other examples ● Open Discussion Agenda
  • 31. Other Applications of Differentiable Rendering
  • 32. Example - NeRF NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis, Mildenhall et al. ECCV Oral 2020 These 3D reconstructions are produced only by using 2D observations.
  • 33. Example - D-NeRF (a.k.a. Nerfies) D-NeRF: Neural Radiance Fields for Dynamic Scenes Pumarola et al. 2020
  • 34. Example - DeepSDF DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation, Park et. al. 2019 Shape as Signed Distance Function
  • 35. Example - Convolutional Occupancy Networks Convolutional Occupancy Networks, Peng et. al. 2020 Occupancy prediction at a 3D point, conditional on input features
  • 36. Example - SIREN Implicit Neural Representations with Periodic Activation Functions, Sitzmann et. al, NeurIPS 2020 (Oral) Replacing the activation layers with periodic functions improves the model’s capacity with same number of parameters
  • 37. There are more algorithms and applications For other algorithms, please check our survey paper Differentiable Rendering: A Survey, H. Kato, D. Beker, M. Morariu, T. Ando, T. Matsuoka, W. Kehl, A. Gaidon