[Submitted on 29 Sep 2026 (v1), last revised 3 Nov 2026 (this version, v3)]
Abstract:Modern image editors excel at semantic manipulation and visual synthesis, yet remain limited in precise spatial control, motivating the development of drag-based editing. However, existing drag-based methods often struggle to balance drag accuracy with natural, plausible, and intent-aligned generation. We propose MoRe-Drag, a motion-grounded drag-based editing method. Our key insight is to treat pixel-space warping as coarse motion evidence, and to inject this evidence into the generative sampling trajectory. Specifically, MoRe-Drag performs region-aware latent recomposition over refinement, inpainting, and preservation regions, coupled with stage-adaptive conditioning that progressively shifts from motion-grounded structure formation to semantic refinement. We further support a no-manual-instruction interface by adapting the MLLM-based text encoder for drag-aware instruction inference. Experiments on DragBench-SR and DragBench-DR show that MoRe-Drag substantially improves drag precision over strong base editors and achieves superior drag accuracy among SOTA drag-based methods, while delivering strong semantic consistency and visually realistic results. Project page: this https URL.
Submission history
From: Xinyu Pu [view email]
[v1] Tue, 29 Sep 2026 05:25:38 UTC (17,997 KB)
[v2] Mon, 26 Oct 2026 06:15:16 UTC (18,063 KB)
[v3] Tue, 3 Nov 2026 10:41:14 UTC (18,058 KB)
