Papers › Single Image Reflection Separation via Component Synergy

Single Image Reflection Separation via Component Synergy

19 Aug 2023ICCV 2023 1arXiv:2308.10027archive 2025-07-28

Qiming Hu, Xiaojie Guo

The reflection superposition phenomenon is complex and widely distributed in the real world, which derives various simplified linear and nonlinear formulations of the problem. In this paper, based on the investigation of the weaknesses of existing models, we propose a more general form of the superposition model by introducing a learnable residue term, which can effectively capture residual information during decomposition, guiding the separated layers to be complete. In order to fully capitalize on its advantages, we further design the network structure elaborately, including a novel dual-stream interaction mechanism and a powerful decomposition network with a semantic pyramid encoder. Extensive experiments and ablation studies are conducted to verify our superiority over state-of-the-art approaches on multiple real-world benchmark datasets. Our code is publicly available at https://github.com/mingcv/DSRNet.

PaperPDFConference PDFCodeCode 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="2308.10027")

Code

Syntology Ran 15 of 19 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 14 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mingcv/dsrnet officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

19 samples harvested; 15 ran; 1 honoured the contract we drafted; 4 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.

1ran · honoured contract
14ran
4unverified

Licence: 0 of the 19 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 mingcv/DSRNet. “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.

CABlock mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 654f8f4b6d0a3205 · report
DualStreamGate mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 77d3179c2d9c6f63 · report
FeaturePyramidVGG mingcv/DSRNet/models/arch/dsrnet.py official repository ran Apache-2.0 (permissive) · c9bb839974d4d85b · report
LRM mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 74052a3fb7a2f97a · report
LayerNorm2d mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 8a82b2f718e05361 · report
LayerNormFunction mingcv/DSRNet/models/arch/dsrnet.py official repository ran Apache-2.0 (permissive) · 66c241d4f1e32dc0 · report
MuGIBlock mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 2810085988564f93 · report
R2Block mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · d94f35746a74bf40 · report
SinBlock mingcv/DSRNet/models/arch/dsrnet.py official repository ran fingerprinted Apache-2.0 (permissive) · 168ababdbf84b4a7 · report
compute_grad mingcv/dsrnet/models/losses.py official repository ran fingerprinted Apache-2.0 (permissive) · 0609d7bef0d31894 · report
count_parameters mingcv/dsrnet/util/net_utils.py official repository ran · honoured contract Apache-2.0 (permissive) · f6b944f50d3f15ae · report
get_norm_layer mingcv/dsrnet/models/networks.py official repository ran Apache-2.0 (permissive) · f783b6ca16b40935 · report
init_loss mingcv/dsrnet/models/losses.py official repository ran Apache-2.0 (permissive) · 769152a8894ee12b · report
receptive_field mingcv/dsrnet/models/networks.py official repository ran Apache-2.0 (permissive) · bbf548b3c60a6415 · report
tensor2im mingcv/dsrnet/models/dsrnet_model_sirs.py official repository ran Apache-2.0 (permissive) · fde6f58552ebe4f1 · report
DSRNet mingcv/DSRNet/models/arch/dsrnet.py official repository unverified Apache-2.0 (permissive) · 76e7680e5cd6ad58 · report
DualStreamBlock mingcv/DSRNet/models/arch/dsrnet.py official repository unverified Apache-2.0 (permissive) · 994dd8350d228fcf · report
DualStreamSeq mingcv/DSRNet/models/arch/dsrnet.py official repository unverified Apache-2.0 (permissive) · 727394299ffb7c73 · report
define_D mingcv/dsrnet/models/networks.py official repository unverified Apache-2.0 (permissive) · 3c2906d11efdb30d · report

Tasks

Reflection Removal

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Reflection Removal Real20 DSRNet PSNR 24.23 #3 of 8 Archive leaderboard report
Reflection Removal Real20 DSRNet SSIM 0.82 #3 of 8 Archive leaderboard report
Reflection Removal SIR^2(Objects) DSRNet PSNR 26.28 #3 of 7 Archive leaderboard report
Reflection Removal SIR^2(Objects) DSRNet SSIM 0.914 #3 of 7 Archive leaderboard report
Reflection Removal SIR^2(Postcard) DSRNet PSNR 24.56 #3 of 6 Archive leaderboard report
Reflection Removal SIR^2(Postcard) DSRNet SSIM 0.908 #3 of 6 Archive leaderboard report
Reflection Removal SIR^2(Wild) DSRNet PSNR 25.68 #3 of 6 Archive leaderboard report
Reflection Removal SIR^2(Wild) DSRNet SSIM 0.896 #3 of 6 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