| title | SwiftVR: Real-Time One-Step Generative Video Restoration |
|---|---|
| authors | Jiaqi Yan, Xiangyu Chen, Xinlin Zhong, Haibin Huang, Chi Zhang, Jie Liu, Jiantao Zhou, Xuelong Li |
| date | 2026-06-08 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.09516 |
| upvotes | 18 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders. We present SwiftVR, a streaming one-step generative VR framework that reduces both bottlenecks under a causal chunk-wise protocol. For attention, mask-free shifted-window self-attention gathers each spatial window into a dense tensor via deterministic indexing, keeping all attention calls on the dense scaled dot-product attention path without masks, cyclic shifts, padding, or hardware-specific sparse kernels. Because SwiftVR uses only standard dense SDPA calls, the trained model transfers to consumer GPUs without retraining or custom kernels. For autoencoding, a lightweight Restoration-aware Autoencoder enables fast chunk-wise decoding while preserving reconstruction quality. On a single H100, SwiftVR sustains 31~FPS at 2560x1440 and 14~FPS at 3840x2160, whereas all compared diffusion-based VR baselines exceed the memory limit at 4K. On a consumer RTX~5090, SwiftVR reaches 26~FPS at 1920x1080. To our knowledge, SwiftVR is the first generative VR model to achieve real-time 1080p streaming on a consumer-grade GPU, while attaining strong no-reference perceptual quality with lower inference cost. Project is available at https://h-oliday.github.io/SwiftVR. |
cite
@misc{yan2026swiftvr,
title={SwiftVR: Real-Time One-Step Generative Video Restoration},
author={Jiaqi Yan and Xiangyu Chen and Xinlin Zhong and Haibin Huang and Chi Zhang and Jie Liu and Jiantao Zhou and Xuelong Li},
year={2026},
eprint={2606.09516},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.09516}
}