Picture for Cho-Ying Wu

Cho-Ying Wu

Boosting Generalizability towards Zero-Shot Cross-Dataset Single-Image Indoor Depth by Meta-Initialization

Add code
Sep 04, 2024
Viaarxiv icon

InSpaceType: Dataset and Benchmark for Reconsidering Cross-Space Type Performance in Indoor Monocular Depth

Add code
Aug 25, 2024
Viaarxiv icon

InSpaceType: Reconsider Space Type in Indoor Monocular Depth Estimation

Add code
Sep 24, 2023
Viaarxiv icon

Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction

Add code
May 12, 2023
Viaarxiv icon

Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?

Add code
Mar 18, 2022
Figure 1 for Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Figure 2 for Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Figure 3 for Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Figure 4 for Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?
Viaarxiv icon

Toward Practical Self-Supervised Monocular Indoor Depth Estimation

Add code
Dec 04, 2021
Figure 1 for Toward Practical Self-Supervised Monocular Indoor Depth Estimation
Figure 2 for Toward Practical Self-Supervised Monocular Indoor Depth Estimation
Figure 3 for Toward Practical Self-Supervised Monocular Indoor Depth Estimation
Figure 4 for Toward Practical Self-Supervised Monocular Indoor Depth Estimation
Viaarxiv icon

Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry

Add code
Oct 20, 2021
Figure 1 for Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Figure 2 for Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Figure 3 for Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Figure 4 for Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Viaarxiv icon

Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices

Add code
Apr 21, 2021
Figure 1 for Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices
Figure 2 for Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices
Figure 3 for Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices
Figure 4 for Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices
Viaarxiv icon

Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network

Add code
Apr 16, 2021
Figure 1 for Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network
Figure 2 for Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network
Figure 3 for Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network
Figure 4 for Accurate 3D Facial Geometry Prediction by Multi-Task, Multi-Modal, and Multi-Representation Landmark Refinement Network
Viaarxiv icon

Geometry-Aware Instance Segmentation with Disparity Maps

Add code
Jun 14, 2020
Figure 1 for Geometry-Aware Instance Segmentation with Disparity Maps
Figure 2 for Geometry-Aware Instance Segmentation with Disparity Maps
Figure 3 for Geometry-Aware Instance Segmentation with Disparity Maps
Figure 4 for Geometry-Aware Instance Segmentation with Disparity Maps
Viaarxiv icon