无需辅助信息，实现复杂背景下的稳定视频抠图。
MatAnyone: Stable Video Matting with Consistent Memory Propagation
- 基于自适应记忆融合，跨帧保持主体语义一致。
- 新数据集+训练策略，显著提升抠图稳定性与细节保真度。
- 适合真实场景下高精度视频抠图任务，尤其复杂背景
无辅助信息的人体视频抠图方法依赖输入帧本身，常在复杂或模糊背景中表现不佳。为此，我们提出针对目标指定的视频抠图框架 MatAnyone。基于记忆机制，引入区域自适应记忆融合模块，实现前一帧记忆的自适应整合，确保核心区域语义稳定的同时保留对象边界的精细细节。为增强训练鲁棒性，构建了一个更大、更高质量且多样化的视频抠图数据集。此外，提出一种新颖的训练策略，高效利用大规模分割数据，提升抠图稳定性。结合新网络结构、数据集与训练策略，MatAnyone 在多样真实场景中均实现稳健且精确的视频抠图结果，优于现有方法。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。