Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track
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 propagati...
| Authors | Mingqi Gao, Sijie Li, Jungong Han |
|---|---|
| Primary category | cs.CV |
| Published | 24 March 2026 |
| Last updated at source | 24 March 2026 |
Connected in the knowledge graph
- maximilian-franz/basil-instancesDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.