VRT: A Video Restoration Transformer
Menlo School · University of Würzburg · +1 more institution
Abstract
Video restoration aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which are restricted by frame-by-frame restoration. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction ability. More specifically, VRT is composed of multiple scales, each of which consists of two kinds of modules: temporal reciprocal self attention (TRSA) and parallel warping. TRSA divides the video into…
Citation impact
- FWCI
- 39.11
- Percentile
- 100%
- References
- 88
Authors
8Topics & keywords
- Computer science
- Artificial intelligence
- Computer vision
- Image warping
- Image restoration
- Motion compensation
- Deblurring
- Feature extraction