Image Restoration

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task (1 more in the archive withheld as spam; see /not-shown), 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

18 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

13 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 666 papers with code (1,459 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Noise2Noise: Learning Image Restoration without Clean Data
  12 Mar 2018 21 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 1 pointer-only (licence)
  We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore…
• Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
  29 Jun 2016 17 repositories listed
  In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers.
• Deep Image Prior
  29 Nov 2017 14 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning.
• Simple Baselines for Image Restoration
  10 Apr 2022 13 repositories listed Syntology ran 23 of 30 samples · 7 unverified · 17 pointer-only (licence)
  Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and…
• Restormer: Efficient Transformer for High-Resolution Image Restoration
  18 Nov 2021 13 repositories listed Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
  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.
• Learning Enriched Features for Real Image Restoration and Enhancement
  15 Mar 2020 12 repositories listed Syntology ran 3 of 20 samples · 17 unverified · 3 pointer-only (licence)
  With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
• SwinIR: Image Restoration Using Swin Transformer
  23 Aug 2021 9 repositories listed Syntology ran 30 of 45 samples · 15 unverified · 5 pointer-only (licence)
  In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
• Multi-Stage Progressive Image Restoration
  4 Feb 2021 8 repositories listed Syntology ran 18 of 26 samples · 8 unverified · 25 pointer-only (licence)
  At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
• Old Photo Restoration via Deep Latent Space Translation
  14 Sep 2020 8 repositories listed
  Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to…
• CycleISP: Real Image Restoration via Improved Data Synthesis
  17 Mar 2020 8 repositories listed
  This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
• EnlightenGAN: Deep Light Enhancement without Paired Supervision
  17 Jun 2019 8 repositories listed
  Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data?
• The 2018 PIRM Challenge on Perceptual Image Super-resolution
  20 Sep 2018 8 repositories listed
  This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018.
• Bringing Old Photos Back to Life
  20 Apr 2020 7 repositories listed Syntology ran 2 of 31 samples · 29 unverified · 20 pointer-only (licence)
  Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to…
• DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
  10 Aug 2019 6 repositories listed
  We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
• Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration
  22 Sep 2022 5 repositories listed
  Using this method we can tackle the major issues in training transformer vision models, such as training instability, resolution gaps between pre-training and fine-tuning, and hunger on data.
• NAFSSR: Stereo Image Super-Resolution Using NAFNet
  19 Apr 2022 5 repositories listed
  This paper inherits a strong and simple image restoration model, NAFNet, for single-view feature extraction and extends it by adding cross attention modules to fuse features between views to adapt to binocular scenarios.
• SAR2SAR: a semi-supervised despeckling algorithm for SAR images
  26 Jun 2020 5 repositories listed
  A study with synthetic speckle noise is presented to compare the performances of the proposed method with other state-of-the-art filters.
• HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
  11 May 2020 5 repositories listed
  Existing face restoration researches typically relies on either the degradation prior or explicit guidance labels for training, which often results in limited generalization ability over real-world images with…
• Multi-level Wavelet-CNN for Image Restoration
  18 May 2018 5 repositories listed
  With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.
• Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
  1 Dec 2022 4 repositories listed Syntology ran 12 of 23 samples · 11 unverified
  Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators.
• Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
  15 Nov 2021 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  The HSI representations are highly similar and correlated across the spectral dimension.
• Uformer: A General U-Shaped Transformer for Image Restoration
  6 Jun 2021 4 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 2 pointer-only (licence)
  Powered by these two designs, Uformer enjoys a high capability for capturing both local and global dependencies for image restoration.
• Plug-and-Play Image Restoration with Deep Denoiser Prior
  31 Aug 2020 4 repositories listed Syntology ran 3 of 28 samples · 25 unverified
  Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems.
• Deep Learning-Based Channel Estimation
  13 Oct 2018 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  This scheme considers the pilot values, altogether, as a low-resolution image and uses an SR network cascaded with a denoising IR network to estimate the channel.
• Recurrent Inference Machines for Solving Inverse Problems
  13 Jun 2017 4 repositories listed
  Much of the recent research on solving iterative inference problems focuses on moving away from hand-chosen inference algorithms and towards learned inference.
• Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
  26 Mar 2024 3 repositories listed Syntology ran 13 of 16 samples · 3 unverified
  These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration.
• Denoising Diffusion Models for Plug-and-Play Image Restoration
  15 May 2023 3 repositories listed Syntology ran 13 of 16 samples · 3 unverified · 1 pointer-only (licence)
  Although diffusion models have shown impressive performance for high-quality image synthesis, their potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored.
• Cross Aggregation Transformer for Image Restoration
  24 Nov 2022 3 repositories listed Syntology ran 7 of 11 samples · 4 unverified
  The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the…
• Masked Frequency Modeling for Self-Supervised Visual Pre-Training
  15 Jun 2022 3 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 2 pointer-only (licence)
  We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models.
• MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
  17 Apr 2022 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI).

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.