Li Fuxin

10

Papers

57

Total Citations

Papers (10)

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats

Object Dynamics Modeling with Hierarchical Point Cloud-based Representations

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

Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods

Discriminative Appearance Modeling With Multi-Track Pooling for Real-Time Multi-Object Tracking

Cycle-Consistent Counterfactuals by Latent Transformations

PointConvFormer: Revenge of the Point-Based Convolution

AutoFocusFormer: Image Segmentation off the Grid

PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation

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