Assistant Professor, Westlake University
3 papers at NeurIPS 2025
E-MoFlow unifies egomotion and optical flow estimation through implicit regularizations under a self-supervised paradigm.
SIU3R: the first alignment-free framework for generalizable simultaneous understanding and 3D reconstruction from unposed images.
Given unposed sparse-view images and an arbitrary style image, our method predicts stylized 3D Gaussians in less than a second using a feed-forward network.
