Papers › ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers

ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers

24 May 2023arXiv:2305.15272archive 2025-07-28

Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image matting. We hypothesize that image matting could also be boosted by ViTs and present a new efficient and robust ViT-based matting system, named ViTMatte. Our method utilizes (i) a hybrid attention mechanism combined with a convolution neck to help ViTs achieve an excellent performance-computation trade-off in matting tasks. (ii) Additionally, we introduce the detail capture module, which just consists of simple lightweight convolutions to complement the detailed information required by matting. To the best of our knowledge, ViTMatte is the first work to unleash the potential of ViT on image matting with concise adaptation. It inherits many superior properties from ViT to matting, including various pretraining strategies, concise architecture design, and flexible inference strategies. We evaluate ViTMatte on Composition-1k and Distinctions-646, the most commonly used benchmark for image matting, our method achieves state-of-the-art performance and outperforms prior matting works by a large margin.

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

hustvl/ViTMatte officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
zhengpeng7/birefnet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bilateral Reference for High-Resolution Dichotomous Image Segmentation (arXiv:2401.03407; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
2023-MindSpore-4/Code14 mindsporeSyntology: not harvested report
MS-P3/code7 mindsporeSyntology: not harvested report
MindCode-4/code-5 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTamin: Designing Scalable Vision Models in the Vision-Language Era (arXiv:2404.02132; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
code-implementation1/Code8 mindsporeSyntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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 Composition-1K ViTMatte Conn 14.78 #3 of 13 Archive leaderboard report
Image Matting Composition-1K ViTMatte Grad 6.74 #3 of 13 Archive leaderboard report
Image Matting Composition-1K ViTMatte MSE 3.0 #3 of 13 Archive leaderboard report
Image Matting Composition-1K ViTMatte SAD 20.33 #3 of 13 Archive leaderboard report
Image Matting Distinctions-646 ViTMatte Conn 12.95 #2 of 4 Archive leaderboard report
Image Matting Distinctions-646 ViTMatte Grad 7.03 #2 of 4 Archive leaderboard report
Image Matting Distinctions-646 ViTMatte MSE 0.0015 #2 of 4 Archive leaderboard report
Image Matting Distinctions-646 ViTMatte SAD 17.05 #2 of 4 Archive leaderboard report
Image Matting Distinctions-646 ViTMatte Trimap √ #2 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

Convolution

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