articleIEEE Transactions on Image ProcessingJan 1, 2024Closed access

VRT: A Video Restoration Transformer

Menlo School · University of Würzburg · +1 more institution

PubMed
Indexed incrossrefpubmed

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

178
total citations
FWCI
39.11
Percentile
100%
References
88
Citations per year

Authors

8

Topics & keywords

Keywords
  • Computer science
  • Artificial intelligence
  • Computer vision
  • Image warping
  • Image restoration
  • Motion compensation
  • Deblurring
  • Feature extraction
No related works found for this paper.

Funding