AIを用いた3Dの研究(CVPR2020)

C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

Learning to Generate 3D Training Data Through Hybrid Gradient

Robust 3D Self-Portraits in Seconds

Bi3D: Stereo Depth Estimation via Binary Classifications

Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion Prediction

Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image

Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes

FocalMix: Semi-Supervised Learning for 3D Medical Image Detection

Frequency Domain Compact 3D Convolutional Neural Networks

ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes

Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

Boundary-Aware 3D Building Reconstruction From a Single Overhead Image

OASIS: A Large-Scale Dataset for Single Image 3D in the Wild

3D Packing for Self-Supervised Monocular Depth Estimation

Height and Uprightness Invariance for 3D Prediction From a Single View

Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction

Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion

View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning

3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset

X3D: Expanding Architectures for Efficient Video Recognition

Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation

TetraTSDF: 3D Human Reconstruction From a Single Image With a Tetrahedral Outer Shell

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

Deep 3D Portrait From a Single Image

StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images

Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction

TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style

Learning to Dress 3D People in Generative Clothing

Generating 3D People in Scenes Without People

Learning to Transfer Texture From Clothing Images to 3D Humans

3D Photography Using Context-Aware Layered Depth Inpainting

Iteratively-Refined Interactive 3D Medical Image Segmentation With Multi-Agent Reinforcement Learning

Leveraging 2D Data to Learn Textured 3D Mesh Generation

Learning a Neural 3D Texture Space From 2D Exemplars

FroDO: From Detections to 3D Objects

KeypointNet: A Large-Scale 3D Keypoint Dataset Aggregated From Numerous Human Annotations

Connect-and-Slice: An Hybrid Approach for Reconstructing 3D Objects

What You See is What You Get: Exploiting Visibility for 3D Object Detection

SESS: Self-Ensembling Semi-Supervised 3D Object Detection

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

DOPS: Learning to Detect 3D Objects and Predict Their 3D Shapes

Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation

MLCVNet: Multi-Level Context VoteNet for 3D Object Detection

Intelligent Home 3D: Automatic 3D-House Design From Linguistic Descriptions Only

Detailed 2D-3D Joint Representation for Human-Object Interaction

3D Part Guided Image Editing for Fine-Grained Object Understanding