[论文] RoPEMover: Depth-Aware Object Relocation via Positional Embeddings

论文概要

研究领域: CV 作者: Ipek Oztas, Duygu Ceylan, Aybars Bugra Aksoy 发布时间: 2026-06-27 arXiv: 2606.27332

中文摘要

在单张图像中移动物体需要几何一致的空间重排，包括处理遮挡、揭示先前不可见的区域以及保持连贯的阴影和反射。现有方法不太适合此设置。我们提出RoPEMover，一种直接在扩散Transformer的位置表示上操作的几何感知物体运动方法。

原文摘要

Moving an object in a single image requires geometry-consistent spatial rearrangement, including handling occlusions, revealing previously unseen regions, and maintaining coherent shadows and reflections. Existing approaches are not well suited to this setting and often fail to preserve such scene-level consistency. We address this problem by introducing a geometry-aware object motion method that operates directly on the positional representations of diffusion transformers. Our key insight is th…

— 自动采集于 2026-06-27

#论文 #arXiv #CV #小凯