Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 302

The DOI matches its Crossref record; 75 of the 75 references it cites were found in a registry or an index.

VRT: A Video Restoration Transformer

Open access
Liang, Jingyun, Cao, Jiezhang, Fan, Yuchen, Zhang, Kai, Ranjan, Rakesh, Li, Yawei, Timofte, Radu, Van Gool, Luc·2024·IEEE Transactions on Image Processing

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 small clips, on which reciprocal attention is applied for joint motion estimation, feature alignment and feature fusion, while self attention is used for feature extraction. To enable cross-clip interactions, the video sequence is shifted for every other layer. Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping. Experimental results on five tasks, including video super-resolution, video deblurring, video denoising, video frame interpolation and space-time video super-resolution, demonstrate that VRT outperforms the state-of-the-art methods by large margins (up to 2.16dB) on fourteen benchmark datasets. The codes are available at https://github.com/JingyunLiang/VRT.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tip.2024.3372454

Cites

75 of 75 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 75 references

Research works printed but not linked: 6

  1. Huang, Bidirectional recurrent convolutional networks for multi-frame super-resolution, 28, 235
  2. Vaswani, 2017, Attention is all you need, arXiv:1706.03762 · arXiv
  3. Shazeer, 2020, GLU variants improve transformer, arXiv:2002.05202 · arXiv
  4. Niklaus, 2018, A Reimplementation of SPyNet Using PyTorch
  5. Xu, Quadratic video interpolation, 32, 1647
  6. 10.48550/ARXIV.1212.0402 · DOI · Paper page

Cited by

See all 302

Metadata

Authors
Liang, J., Cao, J., Fan, Y., Zhang, K., Ranjan, R., Li, Y., Timofte, R., & Van Gool, L.
Venue
IEEE Transactions on Image Processing
Published
2024
Volume
33
Pages
2171-2182
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
OpenAlex
W4392543517
Cited by
302
References
75
FWCI
34.75
Type
journal article
Language
en
Open access
green
Funders
  • Eidgenössische Technische Hochschule Zürich (ETH Zurich) Fund
  • Huawei Technologies Oy (Finland) Project
  • China Scholarship Council
  • Amazon Web Services
  • Alexander von Humboldt Foundation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: VRT: A Video Restoration Transformer. https://app.cochat.ai/papers/10.1109/tip.2024.3372454
The paper
Liang, J., Cao, J., Fan, Y., Zhang, K., Ranjan, R., Li, Y., Timofte, R., & Van Gool, L. (2024). VRT: A Video Restoration Transformer. IEEE Transactions on Image Processing. https://doi.org/10.1109/tip.2024.3372454

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.