AI RESEARCH
An Effective Solution for the CVPR 2026 8th UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence
arXiv CS.CV
•
ArXi:2606.00522v1 Announce Type: new In this work, we present our solution for the 8th UG2+ Challenge (CVPR 2026) Track 3: Dynamic Object Segmentation in Turbulence (DOST). Our method is built upon the strong baseline framework Segment Any Motion (SegAnyMo), which provides powerful mask generation and motion tracking capabilities. To further boost the segmentation performance under severe atmospheric distortions, we propose two key improvements. First, we employ a data-centric domain adaptation strategy. We significantly expand our.