AIを用いた3Dの研究(ECCV2020)

DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares

Self6D: Self-Supervised Monocular 6D Object Pose Estimation

VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment

House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes

Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset

Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Images

Appearance-Preserving 3D Convolution for Video-based Person Re-identification

Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction

CoReNet: Coherent 3D Scene Reconstruction from a Single RGB Image

SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothing

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation

RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving

Collaborative Learning of Gesture Recognition and 3D Hand Pose Estimation with Multi-Order Feature Analysis

Image-to-Voxel Model Translation for 3D Scene Reconstruction and Segmentation

Atlas: End-to-End 3D Scene Reconstruction from Posed Images

Deformation-Aware 3D Model Embedding and Retrieval

Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes

AtlantaNet: Inferring the 3D Indoor Layout from a Single 360(∘) Image beyond the Manhattan World Assumption

Monocular 3D Object Detection via Feature Domain Adaptation

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

Modeling 3D Shapes by Reinforcement Learning

Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop

General 3D Room Layout from a Single View by Render-and-Compare

Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image

Hidden Footprints: Learning Contextual Walkability from 3D Human Trails

RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition

CLOTH3D: Clothed 3D Humans

NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image

Rotation-robust Intersection over Union for 3D Object Detection

3D Scene Reconstruction from a Single Viewport

Eyeglasses 3D shape reconstruction from a single face image

Gen-LaneNet: a generalized and scalable approach for 3D lane detection