Browse State-of-the-Art › Shadow Removal
Shadow Removal
71 papers with code · 5 benchmarks · 9 datasets archive 2025-07-28
Image Shadow Removal
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task (1 more in the archive withheld as spam; see /not-shown), 5 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 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): ISTD+ (1 judged, 1 placed), SRD (1 judged, 0 placed), WSRD+ (1 judged, 1 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ISTD+ (26 rows) | RASM | Regional Attention for Shadow Removal | code | — | Compare |
| SRD (25 rows) | RASM | Regional Attention for Shadow Removal | code | — | Compare |
| ISTD (10 rows) | ShadowFormer | ShadowFormer: Global Context Helps Image Shadow Removal | code | — | Compare |
| INS Dataset (1 row) | OmniSR | OmniSR: Shadow Removal under Direct and Indirect Lighting | code | — | Compare |
| WSRD+ (1 row) | ShadowRefiner | ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier... | 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
9 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 127 · with a code link: 71 · where Syntology ran a sample: 6 (5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 127 tagged: 5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 127, 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. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
20 Nov 2019 5 repositories listedWith the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.
-
26 Mar 2019 5 repositories listedThis paper presents a new method for shadow removal using unpaired data, enabling us to avoid tedious annotations and obtain more diverse training samples.
-
7 Dec 2017 5 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Specifically, a shadow image is fed into the first generator which produces a shadow detection mask.
-
20 Nov 2019 3 repositories listedTo our best knowledge, we are the first one to explore residual and illumination for shadow removal.
-
23 Aug 2019 3 repositories listed Syntology official: harvested, nothing ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 11 harvested samples) · 2 pointer-only (licence)Training our model on this new augmented ISTD dataset further lowers the RMSE on the shadow area to 7.
-
1 Jul 2017 3 repositories listedTwo levels of features are derived from the global network and transferred to two parallel networks.
-
27 Aug 2023 2 repositories listedWe handle high-resolution document shadow removal directly via a larger-scale real-world dataset and a carefully designed frequency-aware network.
-
3 Feb 2023 2 repositories listedIt is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.
-
22 Jun 2022 2 repositories listedIn this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image.
-
10 May 2022 2 repositories listedInspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module in a computationally cheap manner and recovers the…
-
1 Feb 2022 2 repositories listedTo address these issues, we first propose a new shadow illumination model for the shadow removal task.
-
1 Jan 2022 2 repositories listedShadow removal, which aims to restore the background in the shadow regions, is challenging due to the highly ill-posed nature.
-
1 Mar 2021 2 repositories listed Syntology community repositories only · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples) · 7 pointer-only (licence)We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the…
-
23 Dec 2020 2 repositories listedInspired by physical models of shadow formation, we use a linear illumination transformation to model the shadow effects in the image that allows the shadow image to be expressed as a combination of the shadow-free…
-
1 Jun 2020 2 repositories listedFor taking advantage of specific properties of document images, a background estimation module is designed for extracting the global background color of the document.
-
22 Apr 2019 2 repositories listedIn this paper, we propose a novel algorithm to rectify illumination of the digitized documents by eliminating shading artifacts.
-
17 Dec 2018 2 repositories listedThe proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the…
-
12 May 2018 2 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner.
-
7 May 2025 1 repository listedDue to adverse atmospheric and imaging conditions, natural images suffer from various degradation phenomena.
-
18 Apr 2025 1 repository listedWhile deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes.
-
21 Nov 2024 1 repository listedShadow, as a natural consequence of light interacting with objects, plays a crucial role in shaping the aesthetics of an image, which however also impairs the content visibility and overall visual quality.
-
2 Oct 2024 1 repository listedShadows can originate from occlusions in both direct and indirect illumination.
-
11 Sep 2024 1 repository listedIn view of this, inspired by the physical model of shadow formation, we introduce novel soft shadow masks specifically designed for shadow removal.
-
23 Jul 2024 1 repository listedSpecifically, we propose a parallel UNets architecture: 1) the local branch performs the patch-based noise estimation in the diffusion process, and 2) the global branch recovers the low-resolution shadow-free images.
-
11 Jul 2024 1 repository listedIn this paper, we are the first to provide a comprehensive survey to cover various aspects ranging from technical details to applications.
-
25 Jun 2024 1 repository listedTo fill this gap, we propose a weakly supervised shadow removal network with a spherical feature space, dubbed S2-ShadowNet, to explore the best of both worlds for visible and infrared modalities.
-
29 Apr 2024 1 repository listedTransformer recently emerged as the de facto model for computer vision tasks and has also been successfully applied to shadow removal.
-
18 Apr 2024 1 repository listedIn this paper we present S3R-Net, the Self-Supervised Shadow Removal Network.
-
18 Apr 2024 1 repository listedShadow-affected images often exhibit pronounced spatial discrepancies in color and illumination, consequently degrading various vision applications including object detection and segmentation systems.
-
27 Mar 2024 1 repository listedHowever, existing works often simplify this task within the context of shadow removal, limiting the light sources to one and oversimplifying the scene, thus excluding complex self-shadows and restricting surface classes…
-
13 Mar 2024 1 repository listed
-
1 Jan 2024 1 repository listed
-
25 Nov 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
2 Oct 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 4 pointer-only (licence)
-
13 Sep 2023 1 repository listed
-
2 Aug 2023 1 repository listed
-
1 Jun 2023 1 repository listed
-
19 May 2023 1 repository listed
-
5 May 2023 1 repository listed
-
17 Apr 2023 1 repository listed
-
22 Mar 2023 1 repository listed
-
3 Mar 2023 1 repository listed
-
10 Feb 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
9 Dec 2022 1 repository listed
-
8 Dec 2022 1 repository listed
-
30 Nov 2022 1 repository listed
-
27 Nov 2022 1 repository listed
-
15 Nov 2022 1 repository listed
-
9 Nov 2022 1 repository listed
-
18 Oct 2022 1 repository listed
-
6 Sep 2022 1 repository listed
-
27 Aug 2022 1 repository listed
-
21 Jul 2022 1 repository listed
-
20 Mar 2022 1 repository listed
-
23 Aug 2021 1 repository listed
-
7 Aug 2021 1 repository listed
-
19 Apr 2021 1 repository listed
-
24 Mar 2021 1 repository listed
-
5 Jan 2021 1 repository listed
-
4 Dec 2020 1 repository listed
-
29 Nov 2020 1 repository listed
-
3 Oct 2020 1 repository listed
-
28 Jun 2020 1 repository listed
-
9 Apr 2020 1 repository listed
-
26 Aug 2019 1 repository listed
-
20 May 2019 1 repository listed
-
15 Nov 2018 1 repository listed
-
13 Sep 2018 1 repository listed
-
18 Apr 2018 1 repository listed
-
2 Aug 2016 1 repository listed
-
FASR-Net: Unsupervised Shadow Removal Leveraging Inherent Frequency Priors8 Apr 2025 0 repositories listed
-
Leveraging Contrast Information for Efficient Document Shadow Removal1 Apr 2025 0 repositories listed
-
Prompt-Aware Controllable Shadow Removal25 Jan 2025 0 repositories listed
-
Towards Hard and Soft Shadow Removal via Dual-Branch Separation Network and Vision Transformer3 Jan 2025 0 repositories listed
-
SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal1 Jan 2025 0 repositories listed
-
Detail-Preserving Latent Diffusion for Stable Shadow Removal23 Dec 2024 0 repositories listed
-
Controlling the Latent Diffusion Model for Generative Image Shadow Removal via Residual Generation3 Dec 2024 0 repositories listed
-
WavShadow: Wavelet Based Shadow Segmentation and Removal8 Nov 2024 0 repositories listed
-
ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removal5 Nov 2024 0 repositories listed
-
Generative Portrait Shadow Removal7 Oct 2024 0 repositories listed
-
Shadow Removal Refinement via Material-Consistent Shadow Edges10 Sep 2024 0 repositories listed
-
Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal7 Aug 2024 0 repositories listed
-
Semantic-guided Adversarial Diffusion Model for Self-supervised Shadow Removal1 Jul 2024 0 repositories listed
-
Accurate Tennis Court Line Detection on Amateur Recorded Matches10 Apr 2024 0 repositories listed
-
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks15 Mar 2024 0 repositories listed
-
FieldNet: Efficient Real-Time Shadow Removal for Enhanced Vision in Field Robotics13 Mar 2024 0 repositories listed
-
7 Feb 2024 0 repositories listed
-
Recasting Regional Lighting for Shadow Removal1 Feb 2024 0 repositories listed
-
Neural Spline Fields for Burst Image Fusion and Layer Separation21 Dec 2023 0 repositories listed
-
Latent Feature-Guided Diffusion Models for Shadow Removal4 Dec 2023 0 repositories listed
-
DECDM: Document Enhancement using Cycle-Consistent Diffusion Models16 Nov 2023 0 repositories listed
-
Progressive Recurrent Network for Shadow Removal1 Nov 2023 0 repositories listed
-
Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal21 Sep 2023 0 repositories listed
-
DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal28 Jul 2023 0 repositories listed
-
Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal18 May 2023 0 repositories listed
-
Learning Physical-Spatio-Temporal Features for Video Shadow Removal16 Mar 2023 0 repositories listed
-
Structure-Informed Shadow Removal Networks9 Jan 2023 0 repositories listed
-
Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal1 Jan 2023 0 repositories listed
-
Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition1 Jan 2023 0 repositories listed
Syntology lines on 6 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