# CVPR2020 まとめ

- Program： http://cvpr2020.thecvf.com/program/main-conference
- proceedings： http://openaccess.thecvf.com/CVPR2020.py
- シアトルと日本は16時間時差があるので、時差を考慮した日付を入力

## 興味をもった論文
### O君
- GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Moels
- Epipolar Transformers
- Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
- 4D association graph
- DeepCap

## 月曜 6/15
### 01:00-09:00(アジア時間にも開催されるのか不明)
- Tutorial: Disentangled 3D Representations for Relightable Performance Capture of Humans
- https://augmentedperception.github.io/cvpr2020/
### 12:30-16:45
- Workshop: DynaVis: The 2nd International Workshop on Dynamic Scene Reconstruction
- https://dynavis.github.io/2020/
- CMUのOpenPoseの教授も登壇
- 映像: https://www.youtube.com/watch?v=CqjtH_zpbfk
- Learning 3D Generative Models
- https://learn3dgen.github.io/
- アーカイブ配信あり

## 火曜 6/16

### 01:00--06:00
- Tutorial: Neural Rendering
- ライブ配信のみ。
- Tutorial: Learning and Understanding Single Image Depth Estimation in the Wild
- https://sites.google.com/view/cvpr-2020-depth-from-mono/home
- アーカイブ配信あり
- Tutorial: Local Features: From SIFT to Differentiable Methods
- https://local-features-tutorial.github.io/
- おそらくアーカイブ配信あり

### 時間不明(Fulldayという情報のみ)
- Workshop: Fourth Workshop on Computer Vision for AR/VR
- https://mixedreality.cs.cornell.edu/workshop/2020/program
- Tutorial: Visual Recognition for Images, Video, and 3D
- http://s9xie.github.io/Tutorials/CVPR2020/
- Facebookのポーズ推定・物体認識のチームが中心

## 水曜 6/17
### 13:00-14:00(恐らく)
- Satya Nadella氏(MicrosoftのCEO)のプレナリートーク

### 14:00-16:00
- 3D From a Single Image and Shape-From-X (1)
- Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild
- PIFuHD
- 1枚の画像から全身アバターを生成
- Action and Behavior
- Adversarial Learning
- 3D From a Single Image and Shape-From-X; Action and Behavior Recognition; Adversarial Learning
- Self-Supervised Human Depth Estimation From Monocular Videos
- VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines
- Lightweight Photometric Stereo for Facial Details Recovery
- AvatarMe: Realistically Renderable 3D Facial Reconstruction “In-the-Wild”
- 高解像度の顔モデルの生成

### 16:00-18:00
- 3D From Multiview and Sensors (1)
- 4D Association Graph for Realtime Multi-Person Motion Capture Using Multiple Video Cameras
- 清華大。複数カメラからリアルタイムに複数人の3Dポーズ推定
- Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
- 透明物体の3D形状を複数枚のスマホ映像から3次元復元
- Robust 3D Self-portraits in Seconds
- KinectFusion と PIFu 的アプローチを組み合わせた Kinect からの３次元再構成
- Computational Photography
- Efficient Training and Inference
- 3D From Multiview and Sensors; Computational Photography; Efficient Training and Inference Methods for Networks
- Monocular Real-Time Hand Shape and Motion Capture Using Multi-Modal Data
- MPII。単眼カメラからリアルタイムに手のポーズ推定

### 18:00-20:00
- 3D From a Single Image and Shape-From-X (2); 3D From Multiview and Sensors (2)
- Image Retrieval; Datasets and Evaluation
- Low-Level and Physics-Based Vision
- 3D From a Single Image and Shape-From-X; 3D From Multiview and Sensors; Image Retrieval; Datasets and Evaluation; Low-Level and Physics-Based Vision

### 20:00-22:00
- Scene Analysis and Understanding
- Medical, Biological and Cell Microscopy
- Transfer/Low-Shot/Semi/Unsupervised Learning (1)
- Scene Analysis and Understanding; Medical, Biological and Cell Microscopy; Transfer/Low-Shot/Semi/Unsupervised Learning

## 木曜 6/18
### 14:00-16:00
- 3D From Multiview and Sensors (3)
- Face, Gesture, and Body Pose (1)
- EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera
- MPII。イベントカメラでポーズ推定
- DeepCap: Monocular Human Performance Capture Using Weak Supervision
- MPII。単眼カメラで高精度モーションキャプチャ
- Image and Video Synthesis (1)
- 3D From Multiview and Sensors; Face, Gesture, and Body Pose; Image and Video Synthesis
- VIBE: Video Inference for Human Body Pose and Shape Estimation
- MPII。単眼ビデオ映像から単一人のポーズ推定

### 16:00-18:00
- Face, Gesture, and Body Pose (2)
- StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images
- MPII。単眼画像から異なる方向・リグでの顔画像を生成
- Generating 3D People in Scenes Without People
- MPII。部屋の３D画像に、即すような３D人間を配置。
- GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models
- 昨年のマネキンチャレンジ論文のメンバ(google)。
- 3D Human Mesh Regression With Dense Correspondence
- Motion and Tracking (1)
- Representation Learning
- Face, Gesture, and Body Pose; Motion and Tracking; Representation Learning
- DeepDeform: Learning Non-Rigid RGB-D Reconstruction With Semi-Supervised Data
- MPII。ダイナミックフュージョン
- HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map
- MPII。単眼深度画像から手のポーズ推定
- Learning to Dress 3D People in Generative Clothing
- MPII。SMPL関係

### 18:00-20:00
- Face, Gesture, and Body Pose (3); Motion and Tracking (2)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style
- Image and Video Synthesis (2); Neural Generative Models
- Optimization and Learning Methods
- Face, Gesture, and Body Pose; Motion and Tracking; Image and Video Synthesis; Nearal Generative Models; Optimization and Learning Methods
- Wish You Were Here: Context-Aware Human Generation
- 画像に追加で人を入れる手法について。コンテクストを考慮したアプローチ

### 20:00-22:00
- Segmentation, Grouping and Shape (1)
- Explainable AI; Fairness, Accountability, Transparency and Ethics in Vision
- Transfer/Low-Shot/Semi/Unsupervised Learning (2)
- Segmentaiton, Grouping and Shape; Explainable AI; Fairness, Accountability, Transparency and Ethics in Vision; Transfer/Low-Shot/Semi/Unsupervised Learning

## 金曜 6/19
### 13:00-15:00
- Recognition (Detection, Categorization) (1)
- Video Analysis and Understanding
- Vision & Language
- Recognition (Detection, Categorization); Video Analysis and Understanding; Vision + Language

### 15:00-17:00
- Recognition (Detection, Categorization) (2)
- Vision for Robotics and Autonomous Vehicles
- Machine Learning Architectures and Formulations
- Recognition (Detection, Categorization); Vision for Robotics and Autonomous Vehicles; Machine Learning Architectures and Formulations

### 18:00-19:00(恐らく)
- Charlie Bell氏(AWSのSVP)のプレナリートーク

### 19:00-21:00
- Recognition (Detection, Categorization) (3); Segmentation, Grouping and Shape (2)
- Vision Applications and Systems; Vision & Other Modalities; Visual Reasoning and Logical Representation
- Transfer/Low-Shot/Semi/Unsupervised Learning (3)
- Recognition (Detection, Categorization); Segmentation, Grouping and Shape; Vision Applications and Systems; Vision & Other Modalities; Transfer/Low-Shot/Semi/Unsupervised Learning

### 21:00-23:00
- Miscellaneous

## 土曜 6/20
### 13:00-20:30
- Workshop: 6th International Workshop on Computer Vision in Sports (CVsports) at CVPR 2020
- https://vap.aau.dk/cvsports/