Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 4,143

The DOI matches its Crossref record; 102 of the 102 references it cites were found in a registry or an index.

Restormer: Efficient Transformer for High-Resolution Image Restoration

Open access
Zamir, Syed Waqas, Arora, Aditya, Khan, Salman, Hayat, Munawar, Khan, Fahad Shahbaz, Yang, Ming-Hsuan·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural architectures, Transformers, have shown significant performance gains on natural language and high-level vision tasks. While the Transformer model mitigates the shortcomings of CNNs (i.e., limited receptive field and inadaptability to input content), its computational complexity grows quadratically with the spatial resolution, therefore making it infeasible to apply to most image restoration tasks involving high-resolution images. In this work, we propose an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions, while still remaining applicable to large images. Our model, named Restoration Transformer (Restormer), achieves state-of-the-art results on several image restoration tasks, including image deraining, single-image motion deblurring, defocus deblurring (single-image and dual-pixel data), and image denoising (Gaussian grayscale/color denoising, and real image denoising). The source code and pre-trained models are available at https://github.com/swz30/Restormer.

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/cvpr52688.2022.00564

Cites

102 of 102 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

Research works printed but not linked: 9

  1. kumar, 2021, Colorization transformer, ICLRE
  2. hoffer, 2019, Mix & match training convnets with mixed image sizes for improved accuracy speed and scale resiliency
  3. franzen, 1999, Kodak Lossless True Color Image Suite
  4. lei ba, 2016, Layer normalization
  5. touvron, 2021, Training data-efficient image transformers & distillation through attention, ICML
  6. ashish, 2017, Attention is all you need, NeurlPS
  7. radford, 2018, Improving language understanding by generative pre-training, Technical report OpenAI
  8. zhang, 2019, Residual non-local attention networks for image restoration, ICLRE
  9. xu, 2013, Unnatural 10 sparse representation for natural image deblurring, CVPR

Cited by

See all 4,143

Metadata

Authors
Zamir, S. W., Arora, A., Khan, S., Hayat, M., Khan, F. S., & Yang, M.-H.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
5718-5729
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4225672218
Cited by
4,143
References
102
FWCI
303.73
Type
conference paper
Language
en
Open access
green

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

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.