Picture for Li Fuxin

Li Fuxin

Point Cloud Models Improve Visual Robustness in Robotic Learners

Add code
Apr 29, 2024
Viaarxiv icon

Object Dynamics Modeling with Hierarchical Point Cloud-based Representations

Apr 09, 2024
Figure 1 for Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Figure 2 for Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Figure 3 for Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Figure 4 for Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Viaarxiv icon

Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions

Add code
Feb 26, 2024
Viaarxiv icon

Diverse Shape Completion via Style Modulated Generative Adversarial Networks

Nov 18, 2023
Figure 1 for Diverse Shape Completion via Style Modulated Generative Adversarial Networks
Figure 2 for Diverse Shape Completion via Style Modulated Generative Adversarial Networks
Figure 3 for Diverse Shape Completion via Style Modulated Generative Adversarial Networks
Figure 4 for Diverse Shape Completion via Style Modulated Generative Adversarial Networks
Viaarxiv icon

Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models

Sep 26, 2023
Viaarxiv icon

AutoFocusFormer: Image Segmentation off the Grid

Apr 24, 2023
Figure 1 for AutoFocusFormer: Image Segmentation off the Grid
Figure 2 for AutoFocusFormer: Image Segmentation off the Grid
Figure 3 for AutoFocusFormer: Image Segmentation off the Grid
Figure 4 for AutoFocusFormer: Image Segmentation off the Grid
Viaarxiv icon

Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation

Jan 29, 2023
Figure 1 for Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Figure 2 for Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Figure 3 for Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Figure 4 for Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Viaarxiv icon

Examining the Difference Among Transformers and CNNs with Explanation Methods

Dec 15, 2022
Viaarxiv icon

BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation

Aug 08, 2022
Figure 1 for BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
Figure 2 for BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
Figure 3 for BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
Figure 4 for BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
Viaarxiv icon

PointConvFormer: Revenge of the Point-based Convolution

Aug 04, 2022
Figure 1 for PointConvFormer: Revenge of the Point-based Convolution
Figure 2 for PointConvFormer: Revenge of the Point-based Convolution
Figure 3 for PointConvFormer: Revenge of the Point-based Convolution
Figure 4 for PointConvFormer: Revenge of the Point-based Convolution
Viaarxiv icon