Papers › Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

3 Nov 2024arXiv:2411.01656archive 2025-07-28

Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu, Jian Sun

All-in-one image restoration has emerged as a practical and promising low-level vision task for real-world applications. In this context, the key issue lies in how to deal with different types of degraded images simultaneously. In this work, we present a Degradation-Aware Residual-Conditioned Optimal Transport (DA-RCOT) approach that models (all-in-one) image restoration as an optimal transport (OT) problem for unpaired and paired settings, introducing the transport residual as a degradation-specific cue for both the transport cost and the transport map. Specifically, we formalize image restoration with a residual-guided OT objective by exploiting the degradation-specific patterns of the Fourier residual in the transport cost. More crucially, we design the transport map for restoration as a two-pass DA-RCOT map, in which the transport residual is computed in the first pass and then encoded as multi-scale residual embeddings to condition the second-pass restoration. This conditioning process injects intrinsic degradation knowledge (e.g., degradation type and level) and structural information from the multi-scale residual embeddings into the OT map, which thereby can dynamically adjust its behaviors for all-in-one restoration. Extensive experiments across five degradations demonstrate the favorable performance of DA-RCOT as compared to state-of-the-art methods, in terms of distortion measures, perceptual quality, and image structure preservation. Notably, DA-RCOT delivers superior adaptability to real-world scenarios even with multiple degradations and shows distinctive robustness to both degradation levels and the number of degradations.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2411.01656")

Code

Syntology Ran 6 of 6 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xl-tang3/DA-RCOT officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 6 ran; 3 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
2ran · fixture could not drive it

Licence: 6 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from xl-tang3/RCOT. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

calculate_valid_crop_size xl-tang3/RCOT/utils.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 8d1f8f9a430556d7 · report
downsample xl-tang3/RCOT/utils.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 44edb0056e842ff7 · report
upsample xl-tang3/RCOT/utils.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 2ee51c9549987894 · report
PSNR identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · f4c99d0f2598f605 · report
adjust_learning_rate identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · 9496ce74f56e1d57 · report
get_parameter_number identical code first harvested elsewhere ran · honoured contract licence of this copy not recorded · a23501ebdd938df8 · report

Tasks

5-Degradation Blind All-in-One Image RestorationBlind All-in-One Image RestorationImage RestorationUnified Image Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
5-Degradation Blind All-in-One Image Restoration 5-Degradation Blind All-in-One Image Restoration DA-RCOT Average PSNR 30.40 #2 of 7 Archive leaderboard report
5-Degradation Blind All-in-One Image Restoration 5-Degradation Blind All-in-One Image Restoration DA-RCOT LPIPS 0.064 #2 of 7 Archive leaderboard report
Blind All-in-One Image Restoration 3-Degradations DA-RCOT Average PSNR 32.60 #5 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 3-Degradations DA-RCOT SSIM 0.917 #5 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 5-Degradations DA-RCOT Average PSNR 30.40 #3 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 5-Degradations DA-RCOT LPIPS 0.064 #3 of 9 Archive leaderboard report
Blind All-in-One Image Restoration 5-Degradations DA-RCOT SSIM 0.911 #3 of 9 Archive leaderboard report
Unified Image Restoration BSD68 sigma25 DA-RCOT Average PSNR (dB) 31.23 #1 of 1 Archive leaderboard report
Unified Image Restoration GoPro DA-RCOT Average PSNR (dB) 28.68 #1 of 1 Archive leaderboard report
Unified Image Restoration LOL DA-RCOT Average PSNR (dB) 23.25 #1 of 1 Archive leaderboard report
Unified Image Restoration RESIDE DA-RCOT Average PSNR (dB) 31.26 #1 of 1 Archive leaderboard report
Unified Image Restoration Rain100L DA-RCOT Average PSNR (dB) 38.36 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections