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 anchor regions, coupled with stage-adaptive conditioning that progressively shifts from motion-grounded structure formation to semantic refinement. We further support an instruction-free 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. Code and dataset will be publicly released.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pu, X., Wang, H., Gui, J., & Zhou, P. (2026). Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing. https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing
MLA 9
Pu, Xinyu, et al. "Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing." https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing.
Chicago (author–date)
Pu, Xinyu, Hongsong Wang, Jie Gui, and Pan Zhou. 2026. "Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing." https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing.
Harvard
Pu, X., Wang, H., Gui, J. and Zhou, P. (2026) 'Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing', Available at: https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing.
Vancouver
Pu X, Wang H, Gui J, Zhou P. Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing. https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing
IEEE
X. Pu, H. Wang, J. Gui, and P. Zhou, "Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing," https://omanscience.com/en/articles/drag-as-evidence-motion-grounded-latent-recomposition-for-drag-based-editing.