AI RESEARCH
MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator
arXiv CS.CV
•
ArXi:2512.11782v2 Announce Type: replace Video matting remains limited by the scale and realism of existing datasets. While leveraging segmentation data can enhance semantic stability, the lack of effective boundary supervision often leads to segmentation-like mattes lacking fine details. To this end, we