Picture for Zhipeng Zhou

Zhipeng Zhou

State Key Laboratory of Internet of Things for Smart City, University of Macau

CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo

Add code
May 17, 2023
Viaarxiv icon

Semi-supervised Deep Multi-view Stereo

Add code
Jul 24, 2022
Figure 1 for Semi-supervised Deep Multi-view Stereo
Figure 2 for Semi-supervised Deep Multi-view Stereo
Figure 3 for Semi-supervised Deep Multi-view Stereo
Figure 4 for Semi-supervised Deep Multi-view Stereo
Viaarxiv icon

Rethinking the Zigzag Flattening for Image Reading

Add code
Mar 15, 2022
Figure 1 for Rethinking the Zigzag Flattening for Image Reading
Figure 2 for Rethinking the Zigzag Flattening for Image Reading
Figure 3 for Rethinking the Zigzag Flattening for Image Reading
Figure 4 for Rethinking the Zigzag Flattening for Image Reading
Viaarxiv icon

CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning

Add code
Jan 20, 2022
Figure 1 for CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Figure 2 for CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Figure 3 for CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Figure 4 for CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning
Viaarxiv icon

Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports

Add code
Nov 27, 2021
Figure 1 for Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports
Figure 2 for Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports
Figure 3 for Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports
Figure 4 for Achieving an Accurate Random Process Model for PV Power using Cheap Data: Leveraging the SDE and Public Weather Reports
Viaarxiv icon

Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos

Add code
Sep 15, 2021
Figure 1 for Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Figure 2 for Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Figure 3 for Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Figure 4 for Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
Viaarxiv icon

Scaled ReLU Matters for Training Vision Transformers

Add code
Sep 08, 2021
Figure 1 for Scaled ReLU Matters for Training Vision Transformers
Figure 2 for Scaled ReLU Matters for Training Vision Transformers
Figure 3 for Scaled ReLU Matters for Training Vision Transformers
Figure 4 for Scaled ReLU Matters for Training Vision Transformers
Viaarxiv icon

Digging into Uncertainty in Self-supervised Multi-view Stereo

Add code
Sep 08, 2021
Figure 1 for Digging into Uncertainty in Self-supervised Multi-view Stereo
Figure 2 for Digging into Uncertainty in Self-supervised Multi-view Stereo
Figure 3 for Digging into Uncertainty in Self-supervised Multi-view Stereo
Figure 4 for Digging into Uncertainty in Self-supervised Multi-view Stereo
Viaarxiv icon

An Efficient Training Approach for Very Large Scale Face Recognition

Add code
Jun 04, 2021
Figure 1 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 2 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 3 for An Efficient Training Approach for Very Large Scale Face Recognition
Figure 4 for An Efficient Training Approach for Very Large Scale Face Recognition
Viaarxiv icon

When to Fold'em: How to answer Unanswerable questions

Add code
May 01, 2021
Figure 1 for When to Fold'em: How to answer Unanswerable questions
Figure 2 for When to Fold'em: How to answer Unanswerable questions
Figure 3 for When to Fold'em: How to answer Unanswerable questions
Figure 4 for When to Fold'em: How to answer Unanswerable questions
Viaarxiv icon