Papers › Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

Trash or Treasure? An Interactive Dual-Stream Strategy for Single Image Reflection Separation

20 Oct 2021NeurIPS 2021 12arXiv:2110.10546archive 2025-07-28

Qiming Hu, Xiaojie Guo

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 highly ill-posed nature. Existing deep learning based solutions typically restore the target layers individually, or with some concerns at the end of the output, barely taking into account the interaction across the two streams/branches. In order to utilize information more efficiently, this work presents a general yet simple interactive strategy, namely your trash is my treasure (YTMT), for constructing dual-stream decomposition networks. To be specific, we explicitly enforce the two streams to communicate with each other block-wisely. Inspired by the additive property between the two components, the interactive path can be easily built via transferring, instead of discarding, deactivated information by the ReLU rectifier from one stream to the other. Both ablation studies and experimental results on widely-used SIRS datasets are conducted to demonstrate the efficacy of YTMT, and reveal its superiority over other state-of-the-art alternatives. The implementation is quite simple and our code is publicly available at $\href{https://github.com/mingcv/YTMT-Strategy}{\textit{https://github.com/mingcv/YTMT-Strategy}}$.

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="2110.10546")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 4 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/ytmt-strategy 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

8 samples harvested; 4 ran; 0 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 · our draft was wrong
3ran
4unverified

Licence: 0 of the 8 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/ytmt-strategy. “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.

compute_gradient mingcv/ytmt-strategy/models/losses.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 91bda7c651d2e3f7 · report
get_norm_layer mingcv/ytmt-strategy/models/networks.py official repository ran Apache-2.0 (permissive) · f783b6ca16b40935 · report
receptive_field mingcv/ytmt-strategy/models/networks.py official repository ran Apache-2.0 (permissive) · 805fb9818f986a0d · report
tensor2im mingcv/ytmt-strategy/models/opt_ytmt_model_sirs.py official repository ran Apache-2.0 (permissive) · fde6f58552ebe4f1 · report
define_D mingcv/ytmt-strategy/models/networks.py official repository unverified Apache-2.0 (permissive) · 3c2906d11efdb30d · report
l1_norm mingcv/ytmt-strategy/models/losses.py official repository unverified Apache-2.0 (permissive) · 2b5e0c6ca822c2df · report
l1_norm_dim mingcv/ytmt-strategy/models/losses.py official repository unverified Apache-2.0 (permissive) · 7e61feb5a42b61ca · report
tensor2im mingcv/ytmt-strategy/models/ytmt_model_intrinsic_decomp.py official repository unverified Apache-2.0 (permissive) · c4a91c5d16ce72c3 · report

Tasks

Reflection Removalblind source separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Reflection Removal Nature YTMT-UCS PSNR 23.85 #4 of 5 Archive leaderboard report
Reflection Removal Nature YTMT-UCS SSIM 0.810 #4 of 5 Archive leaderboard report
Reflection Removal Real20 YTMT-UCT PSNR 23.26 #6 of 8 Archive leaderboard report
Reflection Removal Real20 YTMT-UCT SSIM 0.806 #6 of 8 Archive leaderboard report
Reflection Removal SIR^2(Objects) YTMT-UCT PSNR 24.87 #4 of 7 Archive leaderboard report
Reflection Removal SIR^2(Objects) YTMT-UCT SSIM 0.896 #4 of 7 Archive leaderboard report
Reflection Removal SIR^2(Postcard) YTMT-UCT PSNR 22.91 #5 of 6 Archive leaderboard report
Reflection Removal SIR^2(Postcard) YTMT-UCT SSIM 0.884 #5 of 6 Archive leaderboard report
Reflection Removal SIR^2(Wild) YTMT-UCT PSNR 25.48 #4 of 6 Archive leaderboard report
Reflection Removal SIR^2(Wild) YTMT-UCT SSIM 0.89 #4 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