Papers › Semantic Human Matting

Semantic Human Matting

5 Sep 2018arXiv:1809.01354archive 2025-07-28

Quan Chen, Tiezheng Ge, Yanyu Xu, Zhiqiang Zhang, Xinxin Yang, Kun Gai

Human matting, high quality extraction of humans from natural images, is crucial for a wide variety of applications. Since the matting problem is severely under-constrained, most previous methods require user interactions to take user designated trimaps or scribbles as constraints. This user-in-the-loop nature makes them difficult to be applied to large scale data or time-sensitive scenarios. In this paper, instead of using explicit user input constraints, we employ implicit semantic constraints learned from data and propose an automatic human matting algorithm (SHM). SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks. In practice, simultaneously learning both coarse semantics and fine details is challenging. We propose a novel fusion strategy which naturally gives a probabilistic estimation of the alpha matte. We also construct a very large dataset with high quality annotations consisting of 35,513 unique foregrounds to facilitate the learning and evaluation of human matting. Extensive experiments on this dataset and plenty of real images show that SHM achieves comparable results with state-of-the-art interactive matting methods.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

lizhengwei1992/Semantic_Human_Matting mentioned on GitHubpytorchSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Matting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Matting AIM-500 SHM Conn. 170.67 #5 of 6 Archive leaderboard report
Image Matting AIM-500 SHM Grad. 115.29 #5 of 6 Archive leaderboard report
Image Matting AIM-500 SHM MAD 0.1012 #5 of 6 Archive leaderboard report
Image Matting AIM-500 SHM MSE 0.0921 #5 of 6 Archive leaderboard report
Image Matting AIM-500 SHM SAD 170.44 #5 of 6 Archive leaderboard report
Image Matting AM-2K SHM MAD 0.0102 #6 of 9 Archive leaderboard report
Image Matting AM-2K SHM MSE 0.0068 #6 of 9 Archive leaderboard report
Image Matting AM-2K SHM SAD 17.81 #6 of 9 Archive leaderboard report
Image Matting P3M-10k SHM MAD 0.0125 #5 of 7 Archive leaderboard report
Image Matting P3M-10k SHM MSE 0.0100 #5 of 7 Archive leaderboard report
Image Matting P3M-10k SHM SAD 21.56 #5 of 7 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