Gengshan Yang

14

Papers

477

Total Citations

Papers (14)

SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM

Hierarchical Deep Stereo Matching on High-Resolution Images

Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion

LASR: Learning Articulated Shape Reconstruction From a Monocular Video

Learning To Segment Rigid Motions From Two Frames

BANMo: Building Animatable 3D Neural Models From Many Casual Videos

Reconstructing Animatable Categories From Videos

Distilling Neural Fields for Real-Time Articulated Shape Reconstruction

3D-Aware Conditional Image Synthesis

Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis

PPR: Physically Plausible Reconstruction from Monocular Videos

Volumetric Correspondence Networks for Optical Flow

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild