Yang Fei

Computer Science and Mathematics undergraduate @ HKUST

Publications

Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation

Yang Fei, George Stoica, Jingyuan Liu, Qifeng Chen†, Ranjay Krishna*, Xiaojuan Wang*, Benlin Liu*†

Under Review

TL;DR: We introduce an algorithm to distill structure-preserving motion priors from an autoregressive video tracking model (SAM2) into a bidirectional video diffusion model.

Paper Project Page

Large Motion Video Autoencoding with Cross-modal Video VAE

Yazhou Xing*, Yang Fei*, Yingqing He*†, Jingye Chen, Jiaxin Xie, Xiaowei Chi, Qifeng Chen†

International Conference on Computer Vision (ICCV), 2025

TL;DR: We propose a video autoencoder that achieves high-fidelity video encoding by combining temporal-aware spatial compression, lightweight temporal compression, and textual guidance.

Paper Project Page Code