Papers › ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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