Research

Paper

TESTING March 24, 2026

Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track

Authors

Mingqi Gao, Sijie Li, Jungong Han

Abstract

This technical report explores the MOSEv2 track of the PVUW 2026 Challenge, which targets complex semi-supervised video object segmentation. Built on SAM~3, we develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance, severe transformation, and strong same-category distractors. Our method first applies the SAM~3 detector to later frames to identify same-category object candidates, and then performs DINOv3-based object-level matching with a transformation-aware target feature pool to retrieve reliable target anchors. These anchors are injected back into the SAM~3 tracker together with the first-frame mask, enabling multi-anchor propagation rather than relying solely on the initial prompt. This simple directly benefits several core challenges of MOSEv2. Our solution achieves a J&F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.

Metadata

arXiv ID: 2603.23788
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-24
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23788v1</id>\n    <title>Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track</title>\n    <updated>2026-03-24T23:45:15Z</updated>\n    <link href='https://arxiv.org/abs/2603.23788v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23788v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>This technical report explores the MOSEv2 track of the PVUW 2026 Challenge, which targets complex semi-supervised video object segmentation. Built on SAM~3, we develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance, severe transformation, and strong same-category distractors. Our method first applies the SAM~3 detector to later frames to identify same-category object candidates, and then performs DINOv3-based object-level matching with a transformation-aware target feature pool to retrieve reliable target anchors. These anchors are injected back into the SAM~3 tracker together with the first-frame mask, enabling multi-anchor propagation rather than relying solely on the initial prompt. This simple directly benefits several core challenges of MOSEv2. Our solution achieves a J&amp;F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-24T23:45:15Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Mingqi Gao</name>\n    </author>\n    <author>\n      <name>Sijie Li</name>\n    </author>\n    <author>\n      <name>Jungong Han</name>\n    </author>\n  </entry>"
}