Browse State-of-the-Art › Shadow Detection
Shadow Detection
46 papers with code · 2 benchmarks · 4 datasets 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| CUHK-Shadow (16 rows) | FDRNet (ICCV 2021) (512x512) | Mitigating Intensity Bias in Shadow Detection via Feature... | — | — | Compare |
| SBU / SBU-Refine (16 rows) | SDDNet (MM 2023) (512x512) | SDDNet: Style-guided Dual-layer Disentanglement Network for Shadow... | 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
4 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.
Papers archive 2025-07-28
archive papers tagged: 79 · with a code link: 46 · where Syntology ran a sample: 7 (5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 79 tagged: 5 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 79 of 79, 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.
-
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.
-
23 Jan 2020 3 repositories listedCloud and cloud shadow segmentation are fundamental processes in optical remote sensing image analysis.
-
16 Nov 2019 3 repositories listedThen, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results.
-
29 May 2023 2 repositories listedWe take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP).
-
11 Jul 2022 2 repositories listedThis paper formulates a new problem, instance shadow detection, which aims to detect shadow instance and the associated object instance that cast each shadow in the input image.
-
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.
-
16 Nov 2019 2 repositories listedShadow detection in general photos is a nontrivial problem, due to the complexity of the real world.
-
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.
-
12 Dec 2017 2 repositories listedTo achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN.
-
26 Dec 2024 1 repository listedAs the successor to the Segment Anything Model (SAM), the Segment Anything Model 2 (SAM2) not only improves performance in image segmentation but also extends its capabilities to video segmentation.
-
3 Sep 2024 1 repository listedShadows are created when light encounters obstacles, resulting in regions of reduced illumination.
-
30 Aug 2024 1 repository listedExisting shadow detection models struggle to differentiate dark image areas from shadows.
-
21 Aug 2024 1 repository listedMoreover, we are the first to introduce the Diffusion model for VSD in which we explore a Space-Time Encoded Embedding (STEE) to inject the temporal guidance for Diffusion to conduct shadow detection.
-
16 Aug 2024 1 repository listedBased on this dataset, we propose a Referring Shadow-Track Memory Network (RSM-Net) for addressing the RVSD task.
-
8 Aug 2024 1 repository listed Syntology 3 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; 3 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 3 pointer-only (licence)The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation…
-
7 Aug 2024 1 repository listedIn this case, when the color of the object is similar to that of the shadow, existing methods struggle to achieve accurate detection.
-
15 May 2024 1 repository listedPrecise and efficient cloud and cloud shadow masking methods are required for the automated use of this data.
-
13 Mar 2024 1 repository listedIn this paper, we analyze and discuss ShadowFormer in preparation for the NTIRE2023 Shadow Removal Challenge [1], implementing five key improvements: image alignment, the introduction of a perceptual quality loss…
-
21 Feb 2024 1 repository listedOur key insight to this problem is that existing methods typically learn discriminative shadow features from the whole image globally, covering the full range of intensity values, and may not learn the subtle…
-
15 Nov 2023 1 repository listedTo adapt SAM for shadow images, trainable adapters are inserted into the frozen image encoder of SAM, since the training of the full SAM model is both time and memory consuming.
-
23 Aug 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 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; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data.
-
19 Aug 2023 1 repository listedIn this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic.
-
17 Aug 2023 1 repository listedDespite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds.
-
1 Jun 2023 1 repository listedThe challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-shot learning in this field.
-
26 May 2023 1 repository listedSegment anything model (SAM) has achieved great success in the field of natural image segmentation.
-
19 May 2023 1 repository listedAs a promptable generic object segmentation model, segment anything model (SAM) has recently attracted significant attention, and also demonstrates its powerful performance.
-
18 Apr 2023 1 repository listedWe can even outperform task-specific network models and achieve state-of-the-art performance in the task we tested: camouflaged object detection, shadow detection.
-
20 Mar 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual…
-
1 Jan 2023 1 repository listedIn this paper, we propose a novel method to detect shadows from raw images.
-
30 Nov 2022 1 repository listedShadow removal improves the visual quality and legibility of digital copies of documents.
-
23 Nov 2022 1 repository listed
-
17 Jun 2022 1 repository listed
-
19 Jun 2021 1 repository listed
-
20 Apr 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
11 Mar 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 4 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
5 Jan 2021 1 repository listed
-
4 Dec 2020 1 repository listed
-
24 Nov 2020 1 repository listed
-
1 Jun 2020 1 repository listed
-
9 Nov 2019 1 repository listed
-
26 Aug 2019 1 repository listed
-
20 May 2019 1 repository listed
-
15 Nov 2018 1 repository listed
-
Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection1 Sep 2018 1 repository listed
-
4 Dec 2017 1 repository listed
-
26 Sep 2017 1 repository listed
-
S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applications9 Apr 2025 0 repositories listed
-
FastInstShadow: A Simple Query-Based Model for Instance Shadow Detection10 Mar 2025 0 repositories listed
-
QDCNN: Quantum Deep Learning for Enhancing Safety and Reliability in Autonomous Transportation Systems1 Mar 2025 0 repositories listed
-
MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis3 Dec 2024 0 repositories listed
-
Test-Time Intensity Consistency Adaptation for Shadow Detection10 Oct 2024 0 repositories listed
-
Differentiable Point-based Inverse Rendering5 Dec 2023 0 repositories listed
-
Deep learning segmentation of fibrous cap in intravascular optical coherence tomography images10 Nov 2023 0 repositories listed
-
AI driven shadow model detection in agropv farms16 Apr 2023 0 repositories listed
-
SCOTCH and SODA: A Transformer Video Shadow Detection Framework13 Nov 2022 0 repositories listed
-
Automated segmentation of microvessels in intravascular OCT images using deep learning1 Oct 2022 0 repositories listed
-
Complicated Background Suppression of ViSAR Image For Moving Target Shadow Detection21 Sep 2022 0 repositories listed
-
Learning Shadow Correspondence for Video Shadow Detection30 Jul 2022 0 repositories listed
-
Shadow-Background-Noise 3D Spatial Decomposition Using Sparse Low-Rank Gaussian Properties for Video-SAR Moving Target Shadow Enhancement7 Jul 2022 0 repositories listed
-
Fine-Context Shadow Detection using Shadow Removal20 Sep 2021 0 repositories listed
-
Temporal Feature Warping for Video Shadow Detection29 Jul 2021 0 repositories listed
-
1 Jan 2021 0 repositories listed
-
Stereoscopic Flash and No-Flash Photography for Shape and Albedo Recovery1 Jun 2020 0 repositories listed
-
ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal4 Aug 2019 0 repositories listed
-
Region Refinement Network for Salient Object Detection27 Jun 2019 0 repositories listed
-
1 Jun 2019 0 repositories listed
-
New approach for solar tracking systems based on computer vision, low cost hardware and deep learning19 Sep 2018 0 repositories listed
-
A Reflectance Based Method For Shadow Detection and Removal11 Jul 2018 0 repositories listed
-
1 Oct 2017 0 repositories listed
-
Automatic Spatial Context-Sensitive Cloud/Cloud-Shadow Detection in Multi-Source Multi-Spectral Earth Observation Images: AutoCloud+16 Jan 2017 0 repositories listed
-
Cast and Self Shadow Segmentation in Video Sequences using Interval based Eigen Value Representation28 Aug 2016 0 repositories listed
-
Multi-feature combined cloud and cloud shadow detection in GaoFen-1 wide field of view imagery17 Jun 2016 0 repositories listed
-
Noisy Label Recovery for Shadow Detection in Unfamiliar Domains1 Jun 2016 0 repositories listed
-
Leave-One-Out Kernel Optimization for Shadow Detection1 Dec 2015 0 repositories listed
-
Shadow Optimization from Structured Deep Edge Detection7 May 2015 0 repositories listed
-
Pixel-wise Orthogonal Decomposition for Color Illumination Invariant and Shadow-free Image30 Jun 2014 0 repositories listed
-
Automatic Feature Learning for Robust Shadow Detection1 Jun 2014 0 repositories listed
-
Radar shadow detection in SAR images using DEM and projections7 Sep 2013 0 repositories listed
-
Shadow Detection: A Survey and Comparative Evaluation of Recent Methods4 Apr 2013 0 repositories listed
Syntology lines on 7 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