AI RESEARCH
Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track
arXiv CS.CV
•
ArXi:2603.23788v1 Announce Type: new 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.