Browse State-of-the-Art › Reflection Removal
Reflection Removal
38 papers with code · 5 benchmarks · 3 datasets archive 2025-07-28
Remove the spots from mirror and clear the picture
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 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; 2 placed): Real20 (1 judged, 1 placed), Nature (2 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 |
|---|---|---|---|---|---|
| Real20 (8 rows) | RDNet | Reversible Decoupling Network for Single Image Reflection Removal | code | — | Compare |
| SIR^2(Objects) (7 rows) | RDNet | Reversible Decoupling Network for Single Image Reflection Removal | code | — | Compare |
| SIR^2(Postcard) (6 rows) | RDNet | Reversible Decoupling Network for Single Image Reflection Removal | code | — | Compare |
| SIR^2(Wild) (6 rows) | RDNet | Reversible Decoupling Network for Single Image Reflection Removal | code | — | Compare |
| Nature (5 rows) | DAI | Dereflection Any Image with Diffusion Priors and Diversified Data | 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
3 datasets whose archive record lists this task, ordered by the archive's paper count.
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: 81 · with a code link: 38 · where Syntology ran a sample: 5 (5 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 (5 of 81 tagged: 5 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 81 of 81, 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.
-
15 Nov 2019 3 repositories listedIBCLN is a cascaded network that iteratively refines the estimates of transmission and reflection layers in a manner that they can boost the prediction quality to each other, and information across steps of the cascade…
-
14 Jun 2018 3 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Our loss function includes two perceptual losses: a feature loss from a visual perception network, and an adversarial loss that encodes characteristics of images in the transmission layers.
-
31 Jan 2018 3 repositories listedImage of a scene captured through a piece of transparent and reflective material, such as glass, is often spoiled by a superimposed layer of reflection image.
-
10 Jun 2025 1 repository listedFollowing this paradigm, we collect a Real-world, Diverse, and Pixel-aligned dataset (named OpenRR-1k dataset), which contains 1, 000 high-quality transmission-reflection image pairs collected in the wild.
-
23 Mar 2025 1 repository listedTo this end, we construct a large-scale dataset, PolaRGB, for Polarization-based reflection removal of RGB images, which enables us to train models that generalize effectively across a wide range of real-world scenarios.
-
21 Mar 2025 1 repository listedReflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections.
-
3 Mar 2025 1 repository listedSingle Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image.
-
12 Feb 2025 1 repository listedThe phenomenon of reflection is quite common in digital images, posing significant challenges for various applications such as computer vision, photography, and image processing.
-
11 Dec 2024 1 repository listedIn this paper, we present a novel approach for image reflection removal using a single image.
-
10 Oct 2024 1 repository listedRecent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of…
-
3 Jun 2024 1 repository listedSecondly, we devise a contrastive mask-guided reflection removal network that comprises a newly proposed contrastive guidance interaction block (CGIB).
-
28 Feb 2024 1 repository listedThis paper addresses reflection removal, which is the task of separating reflection components from a captured image and deriving the image with only transmission components.
-
4 Feb 2024 1 repository listedFor the prompt generation, we first propose a prompt pre-training strategy to train a frequency prompt encoder that encodes the ground-truth image into LF and HF prompts.
-
29 Nov 2023 1 repository listedThis research focuses on the issue of single-image reflection removal (SIRR) in real-world conditions, examining it from two angles: the collection pipeline of real reflection pairs and the perception of real reflection…
-
19 Aug 2023 1 repository listed Syntology official (archive's flag): 15 ran · 15 ran (of which 8 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 19 harvested samples) · 1 pointer-only (licence)The reflection superposition phenomenon is complex and widely distributed in the real world, which derives various simplified linear and nonlinear formulations of the problem.
-
1 Aug 2023 1 repository listedTo the best of our knowledge, these two datasets are the first largest-scale UHD datasets for SIRR.
-
1 Jan 2023 1 repository listedThis paper addresses the problem of robust deep single-image reflection removal (SIRR) against adversarial attacks.
-
5 Nov 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images.
-
16 Jul 2022 1 repository listedWhile the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e. g., 4K) images remains an extremely challenging task due to…
-
4 Apr 2022 1 repository listedMeanwhile, diverse testing sets are also provided with different types of reflection and scenes.
-
12 Mar 2022 1 repository listedWith the deep unrolling technique, we build the DURRNet with ProxNets to model natural image priors and ProxInvNets which are constructed with invertible networks to impose the exclusion prior.
-
20 Oct 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 2 pointer-only (licence)Single image reflection separation (SIRS), as a representative blind source separation task, aims to recover two layers, i. e., transmission and reflection, from one mixed observation, which is challenging due to the…
-
11 Aug 2021 1 repository listedSpecifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network's ability to learn to deblur the image.
-
19 Jun 2021 1 repository listedIn this paper, we consider the absorption effect for the problem of single image reflection removal.
-
7 Mar 2021 1 repository listedThe flash-only image is equivalent to an image taken in a dark environment with only a flash on.
-
1 Jan 2021 1 repository listedOur method processes the corrupted image in two stages, a Low Scale Sub-network (LSSNet) to process the lowest scale and a Progressive Inference (PI) stage to process all the higher scales.
-
13 Dec 2020 1 repository listedIt is beneficial to strong reflection detection and substantially improves the quality of reflection removal results.
-
2 Dec 2020 1 repository listedTo be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.
-
9 Oct 2020 1 repository listedIn this work we present the Deep-Masking Generative Network (DMGN), which is a unified framework for background restoration from the superimposed images and is able to cope with different types of noise.
-
2 Apr 2020 1 repository listedWe present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera.
-
28 Mar 2020 1 repository listed
-
27 Jul 2019 1 repository listed
-
26 Apr 2019 1 repository listed
-
1 Apr 2019 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 11 harvested samples) · 1 pointer-only (licence)
-
11 Sep 2018 1 repository listed
-
1 Sep 2018 1 repository listed
-
30 May 2018 1 repository listed
-
11 Aug 2017 1 repository listed
-
Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering8 Jul 2025 0 repositories listed
-
Single Image Reflection Removal via inter-layer Complementarity19 May 2025 0 repositories listed
-
A Generative Approach to High Fidelity 3D Reconstruction from Text Data5 Mar 2025 0 repositories listed
-
DL2G: Degradation-guided Local-to-Global Restoration for Eyeglass Reflection Removal1 Jan 2025 0 repositories listed
-
Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation31 Dec 2024 0 repositories listed
-
Single-image reflection removal via self-supervised diffusion models29 Dec 2024 0 repositories listed
-
Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats3 Oct 2024 0 repositories listed
-
Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation11 Jul 2024 0 repositories listed
-
Learning to Deblur Polarized Images28 Feb 2024 0 repositories listed
-
Single Image Reflection Removal with Reflection Intensity Prior Knowledge6 Dec 2023 0 repositories listed
-
Fooling Polarization-based Vision using Locally Controllable Polarizing Projection31 Mar 2023 0 repositories listed
-
Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition1 Jan 2023 0 repositories listed
-
Improved Multiple-Image-Based Reflection Removal Algorithm Using Deep Neural Networks9 Aug 2022 0 repositories listed
-
Highlight Specular Reflection Separation based on Tensor Low-rank and Sparse Decomposition Using Polarimetric Cues7 Jul 2022 0 repositories listed
-
4 Dec 2021 0 repositories listed
-
A Categorized Reflection Removal Dataset with Diverse Real-world Scenes7 Aug 2021 0 repositories listed
-
Panoramic Image Reflection Removal19 Jun 2021 0 repositories listed
-
ReflectNet - A Generative Adversarial Method for Single Image Reflection Suppression11 May 2021 0 repositories listed
-
Iterative Gradient Encoding Network with Feature Co-Occurrence Loss for Single Image Reflection Removal29 Mar 2021 0 repositories listed
-
Learned Dual-View Reflection Removal1 Oct 2020 0 repositories listed
-
User-assisted Video Reflection Removal7 Sep 2020 0 repositories listed
-
Reflection Separation via Multi-bounce Polarization State Tracing1 Aug 2020 0 repositories listed
-
Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images1 Jun 2020 0 repositories listed
-
What Does Plate Glass Reveal About Camera Calibration?1 Jun 2020 0 repositories listed
-
SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression15 Feb 2020 0 repositories listed
-
Single image reflection removal via learning with multi-image constraints8 Dec 2019 0 repositories listed
-
Controllable Attention for Structured Layered Video Decomposition24 Oct 2019 0 repositories listed
-
Learning to Jointly Generate and Separate Reflections1 Oct 2019 0 repositories listed
-
Separate In Latent Space: Unsupervised Single Image Layer Separation3 Jun 2019 0 repositories listed
-
Reflection Removal Using a Dual-Pixel Sensor1 Jun 2019 0 repositories listed
-
Single Image Reflection Removal Beyond Linearity1 Jun 2019 0 repositories listed
-
Face Image Reflection Removal3 Mar 2019 0 repositories listed
-
Reflection Removal for Large-Scale 3D Point Clouds1 Jun 2018 0 repositories listed
-
Mirror, Mirror, on the Wall, Who's Got the Clearest Image of Them All? - A Tailored Approach to Single Image Reflection Removal29 May 2018 0 repositories listed
-
Benchmarking Single-Image Reflection Removal Algorithms1 Oct 2017 0 repositories listed
-
Video Reflection Removal Through Spatio-Temporal Optimization1 Oct 2017 0 repositories listed
-
Reflection Separation and Deblurring of Plenoptic Images22 Aug 2017 0 repositories listed
-
Anti-Glare: Tightly Constrained Optimization for Eyeglass Reflection Removal1 Jul 2017 0 repositories listed
-
Reflection Removal Using Low-Rank Matrix Completion1 Jul 2017 0 repositories listed
-
Single Image Reflection Suppression1 Jul 2017 0 repositories listed
-
Reflection Removal for In-Vehicle Black Box Videos1 Jun 2015 0 repositories listed
-
Reflection Removal Using Ghosting Cues1 Jun 2015 0 repositories listed
-
Single Image Layer Separation using Relative Smoothness1 Jun 2014 0 repositories listed
Syntology lines on 5 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