{"ID":2827697,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16880","arxiv_id":"2512.16880","title":"ReMeDI: Refined Memory for Disambiguation of Identities with SAM3 in Surgical Segmentation","abstract":"Accurate surgical instrument segmentation in endoscopy is crucial for computer-assisted interventions, yet remains challenging due to frequent occlusions, rapid motion, and long-term instrument re-entry. While SAM3 provides a powerful spatio-temporal framework for video object segmentation, its performance in surgical scenes is limited by indiscriminate memory updates, fixed memory capacity, and weak identity recovery after occlusions. We propose ReMeDI-SAM3, a training-free extension of SAM3, that addresses these limitations through three components: (i) relevance-aware memory filtering with a dedicated occlusion-aware memory for storing pre-occlusion frames, (ii) a piecewise interpolation scheme that expands effective memory capacity, and (iii) a feature-based re-identification module with temporal voting for reliable post-occlusion identity disambiguation. Together, these components mitigate error accumulation and enable reliable recovery after occlusions. Evaluations on EndoVis17, EndoVis18 and CholecSeg8k under a zero-shot setting show mcIoU improvements of around 5.8\\%, 8\\%, and 2\\% respectively, over vanilla SAM3, outperforming even prior training-based approaches.","short_abstract":"Accurate surgical instrument segmentation in endoscopy is crucial for computer-assisted interventions, yet remains challenging due to frequent occlusions, rapid motion, and long-term instrument re-entry. While SAM3 provides a powerful spatio-temporal framework for video object segmentation, its performance in surgical...","url_abs":"https://arxiv.org/abs/2512.16880","url_pdf":"https://arxiv.org/pdf/2512.16880v2","authors":"[\"Valay Bundele\",\"Mehran Hosseinzadeh\",\"Hendrik P. A. Lensch\"]","published":"2025-12-18T18:49:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}