FastVR: Efficient Streaming Video Restoration with One-Step Diffusion
Read the original on arXiv Computer Vision →FastVR is a streaming video restoration framework that uses a one‑step diffusion model to achieve strong restoration quality and temporal consistency while processing 1080p video at 11 FPS on a single H20 GPU. It addresses efficiency bottlenecks by combining a lightweight VAE with chunk‑wise causal attention, and improves inference speed and restoration quality through velocity consistency regularization and continuous trajectory learning during training. Experiments demonstrate that FastVR outperforms diffusion baselines in efficiency and achieves state‑of‑the‑art performance on both synthetic and real‑world benchmarks.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.