Papers › Diffusion for Natural Image Matting

Diffusion for Natural Image Matting

10 Dec 2023arXiv:2312.05915archive 2025-07-28

Yihan Hu, Yiheng Lin, Wei Wang, Yao Zhao, Yunchao Wei, Humphrey Shi

We aim to leverage diffusion to address the challenging image matting task. However, the presence of high computational overhead and the inconsistency of noise sampling between the training and inference processes pose significant obstacles to achieving this goal. In this paper, we present DiffMatte, a solution designed to effectively overcome these challenges. First, DiffMatte decouples the decoder from the intricately coupled matting network design, involving only one lightweight decoder in the iterations of the diffusion process. With such a strategy, DiffMatte mitigates the growth of computational overhead as the number of samples increases. Second, we employ a self-aligned training strategy with uniform time intervals, ensuring a consistent noise sampling between training and inference across the entire time domain. Our DiffMatte is designed with flexibility in mind and can seamlessly integrate into various modern matting architectures. Extensive experimental results demonstrate that DiffMatte not only reaches the state-of-the-art level on the Composition-1k test set, surpassing the best methods in the past by 5% and 15% in the SAD metric and MSE metric respectively, but also show stronger generalization ability in other benchmarks.

PaperPDFCodeCode 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="2312.05915")

Code

Syntology Ran 6 of 7 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 2 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yihanhu-2022/diffmatte officialmentioned in papermentioned on GitHubpytorch 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

7 samples harvested; 6 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
4ran
1unverified

Licence: 7 of the 7 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 yihanhu-2022/diffmatte. “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.

collate_fn yihanhu-2022/diffmatte/inference.py official repository ran no licence file found · pointer only · 270ac29df928dcab · report
compute_mse_loss yihanhu-2022/diffmatte/evaluation.py official repository ran no licence file found · pointer only · 53ea5c5da9c97958 · report
compute_sad_loss yihanhu-2022/diffmatte/evaluation.py official repository ran no licence file found · pointer only · 4366865041daa492 · report
conv1x1 yihanhu-2022/diffmatte/modeling/backbone/res34.py official repository ran · our draft was wrong no licence file found · pointer only · d9def42110729a85 · report
conv3x3 yihanhu-2022/diffmatte/modeling/backbone/res34.py official repository ran · our draft was wrong no licence file found · pointer only · 160bb14bd76201b4 · report
get_data yihanhu-2022/diffmatte/run_one_image.py official repository ran no licence file found · pointer only · 8294e8f4b6a59a20 · report
infer_one_image yihanhu-2022/diffmatte/run_one_image.py official repository unverified no licence file found · pointer only · aceec6c0b4ad13f6 · report

Tasks

DecoderImage Matting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matting AIM-500 DiffMatte Conn. 15.98 #1 of 6 Archive leaderboard report
Image Matting AIM-500 DiffMatte Grad. 15.68 #1 of 6 Archive leaderboard report
Image Matting AIM-500 DiffMatte MAD 0.0098 #1 of 6 Archive leaderboard report
Image Matting AIM-500 DiffMatte MSE 0.0033 #1 of 6 Archive leaderboard report
Image Matting AIM-500 DiffMatte SAD 16.31 #1 of 6 Archive leaderboard report
Image Matting Composition-1K DiffMatte Conn 11.42 #1 of 13 Archive leaderboard report
Image Matting Composition-1K DiffMatte Grad 5.13 #1 of 13 Archive leaderboard report
Image Matting Composition-1K DiffMatte MSE 2.26 #1 of 13 Archive leaderboard report
Image Matting Composition-1K DiffMatte SAD 17.15 #1 of 13 Archive leaderboard report
Image Matting Distinctions-646 DiffMatte Conn 13.29 #1 of 4 Archive leaderboard report
Image Matting Distinctions-646 DiffMatte Grad 7.20 #1 of 4 Archive leaderboard report
Image Matting Distinctions-646 DiffMatte MSE 0.0015 #1 of 4 Archive leaderboard report
Image Matting Distinctions-646 DiffMatte SAD 15.50 #1 of 4 Archive leaderboard report
Image Matting Distinctions-646 DiffMatte Trimap √ #1 of 4 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.

Methods

Diffusion

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