Abstract
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 introduce a learned Matting Quality Evaluator (MQE) that assesses semantic and boundary quality of alpha mattes without ground truth. It produces a pixel-wise evaluation map that identifies reliable and erroneous regions, enabling fine-grained quality assessment. The MQE scales up video matting in two ways: (1) as an online matting-quality feedback during training to suppress erroneous regions, providing comprehensive supervision, and (2) as an offline selection module for data curation, improving annotation quality by combining the strengths of leading video and image matting models. This process allows us to build a large-scale real-world video matting dataset, VMReal, containing 28K clips and 2.4M frames. To handle large appearance variations in long videos, we introduce a reference-frame training strategy that incorporates long-range frames beyond the local window for effective training. Our MatAnyone 2 achieves state-of-the-art performance on both synthetic and real-world benchmarks, surpassing prior methods across all metrics.
Abstract (translated)
视频抠图技术目前受到现有数据集规模和真实性的限制。虽然利用分割数据可以增强语义稳定性，但由于缺乏有效的边界监督，生成的蒙版往往像分割结果一样缺少细节。为此，我们引入了一个学习型抠图质量评估器（MQE），它可以在没有地面实况的情况下评估alpha蒙版的语义和边界质量。该评估器能产生一张像素级别的评价图，指出可靠区域与错误区域，从而实现精细的质量评估。 MQE通过两种方式促进了视频抠图技术的发展：(1) 在训练过程中作为在线反馈机制，抑制错误区域，并提供全面监督；(2) 作为一个离线选择模块用于数据整理，通过结合领先的视频和图像抠图模型的优势来提高标注质量。这一过程使我们能够构建一个大规模的真实世界视频抠图数据集VMReal，包含28,000个片段和240万帧。 为了处理长视频中较大的外观变化，我们引入了一个参考帧训练策略，在训练时结合超出局部窗口的远距离帧，实现有效的模型训练。我们的MatAnyone 2在合成与真实世界基准测试上均达到了最先进的性能，并且在所有评估指标上都超过了先前的方法。
URL
https://arxiv.org/abs/2512.11782
