AI RESEARCH
Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts
arXiv CS.CV
•
ArXi:2604.17115v1 Announce Type: new Interactive video segmentation models such as SAM2 have nstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sparse point prompts are provided on a single frame, their predictions often suffer from temporal instability, including flickering boundaries, object dropout, and inconsistent object extents across frames. These issues limit their reliability in downstream video understanding and control applications.