Browse State-of-the-Art › Blind All-in-One Image Restoration

Blind All-in-One Image Restoration

10 papers with code · 2 benchmarks · 0 datasets archive 2025-07-28

Computer Vision

Blind All-in-One Image Restoration aims to remove various degradations from an input image without prior knowledge of the degradation type or severity. This task is evaluated under two setups: three-degradation and five-degradation.

Three-Degradation Setup:
The objective is to restore images affected by rain, haze, and noise. Training datasets include Rain200L for deraining, RESIDE for dehazing, and WED and BSD400 for denoising with noise levels σ = 15, 25, 50. Evaluation datasets are Rain100L for deraining, SOTS (outdoor) for dehazing, and BSD68 for denoising with σ = 15, 25, 50.

Five-Degradation Setup:
This setup expands to include five common image restoration tasks: rain, haze, noise, blur, and low-light conditions. Training datasets comprise Rain200L for deraining, RESIDE for dehazing, WED and BSD400 for denoising (σ = 25), GoPro for deblurring, and LoLv1 for low-light enhancement. Evaluation uses Rain100L for deraining, SOTS (outdoor) for dehazing, BSD68 for denoising (σ = 25), GoPro for deblurring, and LoLv1 for low-light enhancement.

Performance Metrics:
Model performance is assessed by reporting the average PSNR and SSIM across all evaluation datasets, reflecting the overall capability to handle diverse degradations. This task challenges models to effectively restore images across multiple degradation types without specific knowledge of the degradation, emphasizing versatility and robustness in image restoration techniques.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 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.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
3-Degradations (9 rows) ABAIR Adaptive Blind All-in-One Image Restoration code — Compare
5-Degradations (9 rows) ABAIR Adaptive Blind All-in-One Image Restoration code — Compare

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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 12 · with a code link: 10 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3 of 12 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 12 of 12, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.

Syntology lines on 3 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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