Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
RelayVSR: Large-Small Model Collaboration for Efficient Real-World Video Super-Resolution
Xijun Wang, Xin Li, Zirui Lang +3
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…
cs.CV2026
ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache Routing
Xijun Wang, Xin Li, Suhang Yao +3
Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise generative fidelity. We propose R…