MatAnyone：稳定视频抠图与一致记忆传播

MatAnyone: Stable Video Matting with Consistent Memory Propagation

January 24, 2025

作者: Peiqing Yang, Shangchen Zhou, Jixin Zhao, Qingyi Tao, Chen Change Loy

cs.AI

摘要

不依赖辅助的人类视频抠像方法通常仅依赖输入帧，在处理复杂或模糊背景时常常遇到困难。为了解决这一问题，我们提出了MatAnyone，这是一个专为目标指定视频抠像而设计的强大框架。具体而言，我们基于基于记忆的范式，引入了一个一致的记忆传播模块，通过区域自适应记忆融合，自适应地整合前一帧的记忆。这确保了核心区域的语义稳定性，同时保留了沿着物体边界的细粒度细节。为了进行稳健的训练，我们提出了一个更大、高质量和多样化的视频抠像数据集。此外，我们还融入了一种新颖的训练策略，有效利用大规模分割数据，提升抠像的稳定性。通过这种新的网络设计、数据集和训练策略，MatAnyone在各种真实场景中提供了强大而准确的视频抠像结果，优于现有方法。

English

Auxiliary-free human video matting methods, which rely solely on input frames, often struggle with complex or ambiguous backgrounds. To address this, we propose MatAnyone, a robust framework tailored for target-assigned video matting. Specifically, building on a memory-based paradigm, we introduce a consistent memory propagation module via region-adaptive memory fusion, which adaptively integrates memory from the previous frame. This ensures semantic stability in core regions while preserving fine-grained details along object boundaries. For robust training, we present a larger, high-quality, and diverse dataset for video matting. Additionally, we incorporate a novel training strategy that efficiently leverages large-scale segmentation data, boosting matting stability. With this new network design, dataset, and training strategy, MatAnyone delivers robust and accurate video matting results in diverse real-world scenarios, outperforming existing methods.