Picture for Weizhe Liu

Weizhe Liu

LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image

Add code
May 24, 2024
Figure 1 for LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Figure 2 for LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Figure 3 for LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Figure 4 for LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image
Viaarxiv icon

NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation

Add code
Mar 27, 2024
Figure 1 for NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Figure 2 for NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Figure 3 for NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Figure 4 for NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
Viaarxiv icon

Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane

Add code
Mar 24, 2024
Viaarxiv icon

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

Add code
Jan 31, 2024
Figure 1 for BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
Figure 2 for BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
Figure 3 for BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
Figure 4 for BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
Viaarxiv icon

RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery

Add code
Sep 19, 2023
Viaarxiv icon

Multi-view Tracking Using Weakly Supervised Human Motion Prediction

Add code
Oct 19, 2022
Figure 1 for Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Figure 2 for Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Figure 3 for Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Figure 4 for Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Viaarxiv icon

Learning to Align Sequential Actions in the Wild

Add code
Nov 17, 2021
Figure 1 for Learning to Align Sequential Actions in the Wild
Figure 2 for Learning to Align Sequential Actions in the Wild
Figure 3 for Learning to Align Sequential Actions in the Wild
Figure 4 for Learning to Align Sequential Actions in the Wild
Viaarxiv icon

Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning

Add code
Apr 22, 2021
Figure 1 for Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
Figure 2 for Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
Figure 3 for Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
Figure 4 for Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
Viaarxiv icon

Leveraging Self-Supervision for Cross-Domain Crowd Counting

Add code
Mar 30, 2021
Figure 1 for Leveraging Self-Supervision for Cross-Domain Crowd Counting
Figure 2 for Leveraging Self-Supervision for Cross-Domain Crowd Counting
Figure 3 for Leveraging Self-Supervision for Cross-Domain Crowd Counting
Figure 4 for Leveraging Self-Supervision for Cross-Domain Crowd Counting
Viaarxiv icon

Counting People by Estimating People Flows

Add code
Dec 01, 2020
Figure 1 for Counting People by Estimating People Flows
Figure 2 for Counting People by Estimating People Flows
Figure 3 for Counting People by Estimating People Flows
Figure 4 for Counting People by Estimating People Flows
Viaarxiv icon