Picture for Daeyun Shin

Daeyun Shin

Modular Framework for Visuomotor Language Grounding

Add code
Sep 05, 2021
Figure 1 for Modular Framework for Visuomotor Language Grounding
Figure 2 for Modular Framework for Visuomotor Language Grounding
Figure 3 for Modular Framework for Visuomotor Language Grounding
Viaarxiv icon

Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

Add code
Apr 07, 2020
Figure 1 for Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Figure 2 for Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Figure 3 for Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Figure 4 for Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Viaarxiv icon

Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation

Add code
Feb 27, 2020
Figure 1 for Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Figure 2 for Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Figure 3 for Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Figure 4 for Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation
Viaarxiv icon

Geometric Pose Affordance: 3D Human Pose with Scene Constraints

Add code
May 19, 2019
Figure 1 for Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Figure 2 for Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Figure 3 for Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Figure 4 for Geometric Pose Affordance: 3D Human Pose with Scene Constraints
Viaarxiv icon

Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction

Add code
Feb 18, 2019
Figure 1 for Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
Figure 2 for Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
Figure 3 for Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
Figure 4 for Multi-layer Depth and Epipolar Feature Transformers for 3D Scene Reconstruction
Viaarxiv icon

Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction

Add code
Jun 12, 2018
Figure 1 for Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Figure 2 for Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Figure 3 for Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Figure 4 for Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
Viaarxiv icon

3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera

Add code
Jul 27, 2016
Figure 1 for 3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Figure 2 for 3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Figure 3 for 3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Figure 4 for 3DFS: Deformable Dense Depth Fusion and Segmentation for Object Reconstruction from a Handheld Camera
Viaarxiv icon