SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3

• URL: http://arxiv.org/abs/2601.09699v1
• Date: Wed, 14 Jan 2026 18:52:14 GMT
• Title: SAM3-DMS: Decoupled Memory Selection for Multi-target Video Segmentation of SAM3
• Abstract summary: Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos.<n>We propose SAM3-DMS, a training-free decoupled strategy that utilizes fine-grained memory selection on individual objects.
• Score: 46.0193087664104
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Segment Anything 3 (SAM3) has established a powerful foundation that robustly detects, segments, and tracks specified targets in videos. However, in its original implementation, its group-level collective memory selection is suboptimal for complex multi-object scenarios, as it employs a synchronized decision across all concurrent targets conditioned on their average performance, often overlooking individual reliability. To this end, we propose SAM3-DMS, a training-free decoupled strategy that utilizes fine-grained memory selection on individual objects. Experiments demonstrate that our approach achieves robust identity preservation and tracking stability. Notably, our advantage becomes more pronounced with increased target density, establishing a solid foundation for simultaneous multi-target video segmentation in the wild.

Related papers

• SAM-MT: Real-Time Interactive Multi-Target Video Segmentation [46.0193087664104]
  Segment Anything 2 (SAM2) is an interactive framework for real-time Multi-Target video segmentation.<n>SAM-MT uses explicit queries to represent different individual targets, in parallel with a shared representation for global context.<n>It successfully decouples latency from the number of targets, achieving real-time speed on par with single-target baselines.
  arXiv  Detail & Related papers  (2026-07-09T16:49:57Z)
• SAM 3: Segment Anything with Concepts [93.97262932669081]
  We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts.<n>PCS takes such prompts and returns segmentation masks and identities for all matching object instances.<n>Our model consists of an image-level detector and a memory-based video tracker that share a single backbone.
  arXiv  Detail & Related papers  (2025-11-20T18:59:56Z)
• MIQ-SAM3D: From Single-Point Prompt to Multi-Instance Segmentation via Competitive Query Refinement [0.328418927821443]
  We propose MIQ-SAM3D, a multi-instance 3D segmentation framework with a competitive query optimization strategy.<n>A prompt-conditioned instance-query generator transforms a single point prompt into multiple specialized queries.<n>A hybrid CNN-Transformer encoder injects CNN-derived boundary saliency into ViT self-attention via spatial gating.<n>A competitively optimized query decoder then enables end-to-end, parallel, multi-instance prediction.
  arXiv  Detail & Related papers  (2025-11-03T08:48:28Z)
• SAMSON: 3rd Place Solution of LSVOS 2025 VOS Challenge [9.131199997701282]
  Large-scale Video Object module (LSVOS) addresses the challenge of accurately tracking and segmenting objects in long video sequences.<n>Our method achieved a final performance of 0.8427 in terms of J &F in the test-set leaderboard.
  arXiv  Detail & Related papers  (2025-09-22T08:30:34Z)
• HQ-SMem: Video Segmentation and Tracking Using Memory Efficient Object Embedding With Selective Update and Self-Supervised Distillation Feedback [0.0]
  We introduce HQ-SMem, for High Quality video segmentation and tracking using Smart Memory.<n>Our approach incorporates three key innovations: (i) leveraging SAM with High-Quality masks (SAM-HQ) alongside appearance-based candidate-selection to refine coarse segmentation masks, resulting in improved object boundaries; (ii) implementing a dynamic smart memory mechanism that selectively stores relevant key frames while discarding redundant ones; and (iii) dynamically updating the appearance model to effectively handle complex topological object variations and reduce drift throughout the video.
  arXiv  Detail & Related papers  (2025-07-25T03:28:05Z)
• SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree [79.26409013413003]
  We introduce SAM2Long, an improved training-free video object segmentation strategy.<n>It considers the segmentation uncertainty within each frame and chooses the video-level optimal results from multiple segmentation pathways.<n> SAM2Long achieves an average improvement of 3.0 points across all 24 head-to-head comparisons.
  arXiv  Detail & Related papers  (2024-10-21T17:59:19Z)
• VideoSAM: Open-World Video Segmentation [33.09103541421983]
  We introduce VideoSAM, an end-to-end framework designed to improve object tracking and segmentation consistency in dynamic environments. VideoSAM integrates an agglomerated backbone, RADIO, enabling object association through similarity metrics. Our method is extensively evaluated on the UVO and BURST benchmarks, and robotic videos from RoboTAP, demonstrating its effectiveness and robustness in real-world scenarios.
  arXiv  Detail & Related papers  (2024-10-11T12:56:32Z)
• 3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation [63.199793919573295]
  Video Object (VOS) is a vital task in computer vision, focusing on distinguishing foreground objects from the background across video frames. Our work draws inspiration from the Cutie model, and we investigate the effects of object memory, the total number of memory frames, and input resolution on segmentation performance.
  arXiv  Detail & Related papers  (2024-06-06T00:56:25Z)
• Segment Anything Meets Point Tracking [116.44931239508578]
  This paper presents a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. We highlight the merits of point-based tracking through direct evaluation on the zero-shot open-world Unidentified Video Objects (UVO) benchmark. Our experiments on popular video object segmentation and multi-object segmentation tracking benchmarks, including DAVIS, YouTube-VOS, and BDD100K, suggest that a point-based segmentation tracker yields better zero-shot performance and efficient interactions.
  arXiv  Detail & Related papers  (2023-07-03T17:58:01Z)
• MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization [61.015704878681795]
  We present a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for 3D point clouds. The two non-trivial challenges posed by this multi-scan multibody setting are. guaranteeing correspondence and segmentation consistency across multiple input point clouds and. obtaining robust motion-based rigid body segmentation applicable to novel object categories.
  arXiv  Detail & Related papers  (2021-01-17T06:36:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.