Picture for Chuhang Zou

Chuhang Zou

MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance

Add code
Apr 12, 2024
Viaarxiv icon

QFF: Quantized Fourier Features for Neural Field Representations

Add code
Dec 02, 2022
Viaarxiv icon

Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling

Add code
Oct 14, 2022
Figure 1 for Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
Figure 2 for Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
Figure 3 for Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
Figure 4 for Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling
Viaarxiv icon

Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis

Add code
Jun 14, 2022
Figure 1 for Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
Figure 2 for Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
Figure 3 for Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
Figure 4 for Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis
Viaarxiv icon

PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility

Add code
Aug 19, 2021
Figure 1 for PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility
Figure 2 for PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility
Figure 3 for PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility
Figure 4 for PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility
Viaarxiv icon

Multi-Task Learning from Videos via Efficient Inter-Frame Attention

Add code
Feb 18, 2020
Figure 1 for Multi-Task Learning from Videos via Efficient Inter-Frame Attention
Figure 2 for Multi-Task Learning from Videos via Efficient Inter-Frame Attention
Figure 3 for Multi-Task Learning from Videos via Efficient Inter-Frame Attention
Figure 4 for Multi-Task Learning from Videos via Efficient Inter-Frame Attention
Viaarxiv icon

3D Manhattan Room Layout Reconstruction from a Single 360 Image

Add code
Oct 24, 2019
Figure 1 for 3D Manhattan Room Layout Reconstruction from a Single 360 Image
Figure 2 for 3D Manhattan Room Layout Reconstruction from a Single 360 Image
Figure 3 for 3D Manhattan Room Layout Reconstruction from a Single 360 Image
Figure 4 for 3D Manhattan Room Layout Reconstruction from a Single 360 Image
Viaarxiv icon

Improving Style Transfer with Calibrated Metrics

Add code
Oct 21, 2019
Figure 1 for Improving Style Transfer with Calibrated Metrics
Figure 2 for Improving Style Transfer with Calibrated Metrics
Figure 3 for Improving Style Transfer with Calibrated Metrics
Figure 4 for Improving Style Transfer with Calibrated Metrics
Viaarxiv icon

Counterfactual Depth from a Single RGB Image

Add code
Sep 03, 2019
Figure 1 for Counterfactual Depth from a Single RGB Image
Figure 2 for Counterfactual Depth from a Single RGB Image
Figure 3 for Counterfactual Depth from a Single RGB Image
Figure 4 for Counterfactual Depth from a Single RGB Image
Viaarxiv icon

Silhouette Guided Point Cloud Reconstruction beyond Occlusion

Add code
Jul 29, 2019
Figure 1 for Silhouette Guided Point Cloud Reconstruction beyond Occlusion
Figure 2 for Silhouette Guided Point Cloud Reconstruction beyond Occlusion
Figure 3 for Silhouette Guided Point Cloud Reconstruction beyond Occlusion
Figure 4 for Silhouette Guided Point Cloud Reconstruction beyond Occlusion
Viaarxiv icon