Large generative models can recover realistic detail in real-world video super-resolution (VSR), but processing an entire video with them is computationally expensive. In this work, we present RelayVSR, a streaming VSR framework built on the Sparse Generative Relay mechanism. A large generative model generates referenc...
Xi-Jun Wang, Xin Li, Zi-Rui Lang et al.· 0 citations
ReCaVSR enables streaming VSR without iterative sampling or full historical KV-cache materialization, and Experiments on synthetic and real-world VSR benchmarks show better perceptual quality, temporal consistency, and streaming efficiency than representative VSR baselines.
Xi-Jun Wang, Xin Li, Su-Hang Yao et al.· arXiv.org· 0 citations
The proposed UniDiffFusion framework is trained in a progressive manner to decouple fusion learning, degradation-aware restoration, and application-specific adaptation, thereby reducing interference among heterogeneous objectives.
Xing-Xin Xu, Si-Qi Zhao, Xin Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.