EUVIMEDEUVIMED entdecken
Crossref

Segment and Matte Anything in a Unified Model

Zezhong Fan, Xiaohan Li, Topojoy Biswas, Kaushiki Nag, Kannan Achan

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3813-3821

DOI: 10.1609/aaai.v40i5.37382 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zezhong Fan und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating remarkable zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls short of the precision required in real-world applications. While several refinement modules have been proposed to boost SAM’s segmentation quality, achieving highly accurate object delineation within a single, unified framework remains an open challenge. Furthermore, interactive image matting—which aims to generate fine-grained alpha mattes guided by diverse user hints—has not yet been explored in the context of SAM. Insights from recent studies highlight strong correlations between segmentation and matting, suggesting the feasibility of a unified model capable of both tasks. In this paper, we introduce Segment And Matte Anything (SAMA), a lightweight extension of SAM that delivers high-quality interactive image segmentation and matting with minimal extra parameters or computational cost. Our Multi-View Localization Encoder (MVLE) captures detailed features from local views, while the Localization Adapter (Local-Adapter) refines mask outputs by recovering subtle boundary details. We also incorporate two prediction heads for each task into the architecture to generate segmentation and matting tasks, simultaneously. Trained on a diverse dataset aggregated from publicly available sources, SAMA achieves state-of-the-art performance across multiple segmentation and matting benchmarks, showcasing its adaptability and effectiveness in a wide range of downstream tasks.

Zitieren

APA

Fan, Z., Li, X., Biswas, T., Nag, K., & Achan, K. (2026). Segment and Matte Anything in a Unified Model. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3813-3821. https://doi.org/10.1609/aaai.v40i5.37382

Vancouver

Fan Z, Li X, Biswas T, Nag K, Achan K. Segment and Matte Anything in a Unified Model. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3813-3821. doi:10.1609/aaai.v40i5.37382

BibTeX
@article{Fan2026,
  author = {Fan, Zezhong and Li, Xiaohan and Biswas, Topojoy and Nag, Kaushiki and Achan, Kannan},
  title = {Segment and Matte Anything in a Unified Model},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3813--3821},
  doi = {10.1609/aaai.v40i5.37382}
}
Kostenlos starten →