How I Study AI - Learn AI Papers & Lectures the Easy Way

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

Intermediate

Hau-Shiang Shiu, Chin-Yang Lin et al.Dec 29arXiv

This paper makes diffusion-based video super-resolution (VSR) practical for live, low-latency use by removing the need for future frames and cutting denoising from ~50 steps down to just 4.

#video super-resolution#diffusion model#latent diffusion

Papers1

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion