Siyu Zhang

Siyu Zhang

Auto-generated profile, based on publicly available information

Siyu Zhang

DV.ai, Hangzhou, China

Research Focus & Metrics

Representative Publications

View All Publications
10 August 2025
Verified
Conference Paper
Open access
JSJiaming Sun
Jiaming Sun
SZSiyu Zhang
Siyu Zhang
YZYu Zhang
Yu Zhang
ZXZhen Xu
Zhen Xu
XZXiaowei Zhou
Xiaowei Zhou

9 November 2026 in ACM Transactions on Graphics
Verified
Journal Article
Open access
TLTaoming Liu
Taoming Liu
YSYinji ShenTu
Yinji ShenTu
GHGuangzhao He
Guangzhao He
YJYudong Jin
Yudong Jin
YYYukang Ye
Yukang Ye
XZXiaowei Zhou
Xiaowei Zhou
Accurate lighting response is essential for realistic dynamic human relighting, because shadows, highlights, and color changes should follow the target illumination in both direction and relative strength. Current learning-based relighting methods can generate visually plausible videos, but they often exhibit imprecise lighting responses: shadows and highlights may drift away from the target direction, and the output brightness may not faithfully follow the relative intensities in the target environment, making the result closer to appearance harmonization than controllable relighting. To address this issue, we propose DynOLAT, a generalizable OLAT video prediction framework for dynamic full-body humans. Instead of directly synthesizing a single relit appearance, our method predicts temporally consistent One-Light-At-a-Time (OLAT) basis videos from flat-lit inputs, and then linearly combines the predicted bases according to the target environment map. This OLAT-based formulation makes the directional response explicit in the predicted bases, while the relative lighting strength is determined by the linear weights derived from the environment map. We further introduce a dynamic capture pipeline and the first large-scale dynamic full-body OLAT dataset, comprising over 24 million frames from 224 identity-outfit combinations, where different outfits of the same person define separate combinations. Experiments show that DynOLAT responds more faithfully to variations in target lighting direction and relative intensity than the tested baselines, enabling controllable video relighting while preserving fine appearance details and temporal coherence. The dataset and processing tools will be publicly released to foster future research.

19 November 2026
Verified
Conference Paper
Open access
YSYinji ShenTu
Yinji ShenTu
FXFengze Xie
Fengze Xie
ZYZhiyuan Yu
Zhiyuan Yu
JSJiaming Sun
Jiaming Sun
SZSiyu Zhang
Siyu Zhang
XZXiaowei Zhou
Xiaowei Zhou