{"ID":2870264,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12791","arxiv_id":"2509.12791","title":"Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation","abstract":"Superpixels are widely used in computer vision to simplify image representation and reduce computational complexity. While traditional methods rely on low-level features, deep learning-based approaches leverage high-level features but also tend to sacrifice regularity of superpixels to capture complex objects, leading to accurate but less interpretable segmentations. In this work, we introduce SPAM (SuperPixel Anything Model), a versatile framework for segmenting images into accurate yet regular superpixels. We train a model to extract image features for superpixel generation, and at inference, we leverage a large-scale pretrained model for semantic-agnostic segmentation to ensure that superpixels align with object masks. SPAM can handle any prior high-level segmentation, resolving uncertainty regions, and is able to interactively focus on specific objects. Comprehensive experiments demonstrate that SPAM qualitatively and quantitatively outperforms state-of-the-art methods on segmentation tasks, making it a valuable and robust tool for various applications. Code and pre-trained models are available here: https://github.com/waldo-j/spam.","short_abstract":"Superpixels are widely used in computer vision to simplify image representation and reduce computational complexity. While traditional methods rely on low-level features, deep learning-based approaches leverage high-level features but also tend to sacrifice regularity of superpixels to capture complex objects, leading...","url_abs":"https://arxiv.org/abs/2509.12791","url_pdf":"https://arxiv.org/pdf/2509.12791v1","authors":"[\"Julien Walther\",\"Rémi Giraud\",\"Michaël Clément\"]","published":"2025-09-16T08:09:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609752,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2870264,"paper_url":"https://arxiv.org/abs/2509.12791","paper_title":"Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentation","repo_url":"https://github.com/waldo-j/spam","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}