4 papers
Human3R: Everyone Everywhere All at Once
Yue Chen, Xingyu Chen, Yuxuan Xue +3
We present Human3R, a unified, feed-forward framework for online 4D human-scene reconstruction, in the world frame, from casually captured monocular videos. Unlike previous approac…
TTT3R: 3D Reconstruction as Test-Time Training
Xingyu Chen, Yue Chen, Yuliang Xiu +2
Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly…
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
Xingyu Chen, Yue Chen, Yuliang Xiu +2
Recent advances in DUSt3R have enabled robust estimation of dense point clouds and camera parameters of static scenes, leveraging Transformer network architectures and direct super…
Feat2GS: Probing Visual Foundation Models with Gaussian Splatting
Yue Chen, Xingyu Chen, Anpei Chen +2
Given that visual foundation models (VFMs) are trained on extensive datasets but often limited to 2D images, a natural question arises: how well do they understand the 3D world? Wi…