解决图像合成中物体位置关系混乱问题，实现多物体并行精准融合。
PICS: Pairwise Image Compositing with Spatial Interactions
- 分区域路由专家网络，显式建模物体与背景的交互关系。
- 在虚拟试穿、室内、街景场景中均显著优于现有方法。
- 支持几何变化鲁棒性，适合复杂场景的多对象合成任务。
尽管基于扩散模型的单次图像合成表现良好，但在成对或序列化编辑中常因后续插入覆盖已有内容而破坏空间一致性。本文提出PICS，一种自监督的逐部分合成范式，通过并行方式合成物体，并显式建模（完全/部分）可见物体与背景间的组合交互。核心为交互变压器，利用掩码引导的专家混合机制，将背景、独占区和重叠区分别分配给专用专家，并采用自适应α混合策略，在保留边界清晰度的同时融合重叠物体。为进一步提升对几何变化的鲁棒性，引入涵盖平面外与平面内姿态变化的几何感知增强。大量实验表明，该方法在虚拟试穿、室内和街景场景中均取得优于当前最优基线的合成质量与稳定性。代码与数据已公开于https://github.com/RyanHangZhou/PICS。
原文摘要 · Abstract (English)
Despite strong single-turn performance, diffusion-based image compositing often struggles to preserve coherent spatial relations in pairwise or sequential edits, where subsequent insertions may overwrite previously generated content and disrupt physical consistency. We introduce PICS, a self-supervised composition-by-decomposition paradigm that composes objects in parallel while explicitly modeling the compositional interactions among (fully-/partially-)visible objects and background. At its core, an Interaction Transformer employs mask-guided Mixture-of-Experts to route background, exclusive, and overlap regions to dedicated experts, with an adaptive α-blending strategy that infers a compatibility-aware fusion of overlapping objects while preserving boundary fidelity. To further enhance robustness to geometric variations, we incorporate geometry-aware augmentations covering both out-of-plane and in-plane pose changes of objects. Our method delivers superior pairwise compositing quality and substantially improved stability, with extensive evaluations across virtual try-on, indoor, and street scene settings showing consistent gains over state-of-the-art baselines. Code and data are available at https://github.com/RyanHangZhou/PICS
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。