Abstract
Recent years have witnessed the success of diffusion models in image-customized tasks. Prior works have achieved notable progress on human-oriented erasing using explicit mask guidance and semantic-aware inpainting. However, they struggle under complex multi-IP scenarios involving human-human occlusions, human-object entanglements, and background interferences. These challenges are mainly due to: 1) Dataset limitations, as existing datasets rarely cover dense occlusions, camouflaged backgrounds, and diverse interactions; 2) Lack of spatial decoupling, where foreground instances cannot be effectively disentangled, limiting clean background restoration. In this work, we introduce a high-quality multi-IP human erasing dataset with diverse pose variations and complex backgrounds. We then propose Multi-Layer Diffusion (MILD), a novel strategy that decomposes generation into semantically separated pathways for each instance and the background. To enhance human-centric understanding, we introduce Human Morphology Guidance, integrating pose, parsing, and spatial relations. We further present Spatially-Modulated Attention to better guide attention flow. Extensive experiments show that MILD outperforms state-of-the-art methods on challenging human erasing benchmarks.
Abstract (translated)
近年来，扩散模型在图像定制任务中取得了显著成功。此前的工作已经在使用显式遮罩引导和语义感知修复进行人像擦除方面取得了重要进展。然而，在涉及人物间遮挡、人与物体纠缠以及背景干扰的复杂多IP场景下（其中IP指涉及个体或多个独立实体的情况），这些方法仍面临挑战。这些问题主要源于：1）数据集限制，现有数据集中很少包含密集遮挡、伪装背景和多样化的互动情况；2）缺乏空间解耦能力，前景实例不能有效分离，从而限制了对干净背景的恢复。在这项工作中，我们引入了一个高质量的多IP人物擦除数据集，其中包含了多种姿势变化及复杂的背景。随后，我们提出了多层次扩散（MILD），这是一种新型策略，将生成过程分解为每个实例和背景的语义独立路径。为了增强以人类为中心的理解，我们还介绍了人体形态引导，整合了姿态、解析以及空间关系。此外，我们提出了一种空间调制注意力机制，以更好地指导注意力流。广泛的实验表明，在具有挑战性的人像擦除基准测试中，MILD优于现有的最先进技术。
URL
https://arxiv.org/abs/2508.06543
