Zixiang Zhao

Postdoc, ETHZ - ETH Zurich

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking

#4803 Spotlight · Zixiang Zhao, Haowen Bai, Bingxin Ke, Yukun Cui, Lilun Deng, Yulun Zhang, Kai Zhang, Konrad Schindler

We present UniVF, a unified video fusion framework with multi-frame learning; VF-Bench, the first benchmark covering four video fusion tasks; and a unified spatial–temporal evaluation protocol with a new temporal consistency loss.