Author

Xin Lu

h-index 9 View on Semantic Scholar

We have 1 of 26 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

OmniVR: Joint Video-Audio Conditional Generation for Restoring Degraded Historical Films

OminiVR surpasses all prior methods on all six visual metrics, achieves the best audio quality, and produces natural colorization---the first method to jointly address all three aspects of audio-video generative restoration.

Xin Lu, Zihao Fan, Mingchen Zhong et al. · 1 citation