Summary
RoPEMover is a computer vision paper (arXiv 2606.27332) by Ipek Oztas, Duygu Ceylan, and Aybars Bugra Aksoy that addresses object relocation in single images. Moving an object within one image demands geometry-consistent spatial rearrangement: 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 scene-level consistency. The authors introduce a geometry-aware object motion method that operates directly on the positional representations of diffusion transformers, leveraging rotary positional embeddings (RoPE) to encode depth-aware motion. The post was automatically collected from arXiv and shared on zhichai.net on 2026-06-27.
Paper Overview
- Field: Computer Vision
- Authors: Ipek Oztas, Duygu Ceylan, Aybars Bugra Aksoy
- Release date: 2026-06-27
- arXiv: 2606.27332
Abstract
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.
The authors address this problem by introducing a geometry-aware object motion method that operates directly on the positional representations of diffusion transformers. Their key insight is that... (the original abstract is truncated in the source post; see the arXiv page for the full text).
---
*Auto-collected on 2026-06-27.*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178208208