video-matting

MatAnyone-E is an efficient extension of MatAnyone 2 for high-resolution video matting that applies high-resolution memory matching only to uncertain regions and uses a lightweight decoder, achieving up to 7.4x speedup and reducing peak GPU memory to 7.6% of the original at 4K while preserving matting quality.

VideoMaMa++ 提出一种掩码引导的扩散式视频抠图框架，通过分离的 RGB/掩码 token 流以及 preserve-and-refine 可学习嵌入，实现跨片段边界的滑窗推理，从而在长视频中保持时间一致性并提升细节精度。

SAM2Matting introduces a tracker-to-matting framework that enhances foundational trackers like SAM2 with region-proposal bridges and matting heads, achieving state-of-the-art video matting performance even when trained only on images, with strong generalization across diverse scenarios.