Metraipolis › archive › dc_14bc7c0abe4d
Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing — arXiv:2609.36755
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36755
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:23.976Z
- SHA-256 of the archived text
a37be1dc990937f318c925efb6b3029fa15723a8c017f3c144425e4d623902fd- Stable URL of this page
https://metraipolis.com/documento/dc_14bc7c0abe4d
How to cite
Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing — arXiv:2609.36755 — arXiv (en), https://arxiv.org/abs/2609.36755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14bc7c0abe4d (Metraipolis archive dc_14bc7c0abe4d, sha256 a37be1dc990937f318c925efb6b3029fa15723a8c017f3c144425e4d623902fd)
BibTeX
@misc{dc14bc7c0abe4d,
title = {Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing — arXiv:2609.36755},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36755},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14bc7c0abe4d; sha256 a37be1dc990937f318c925efb6b3029fa15723a8c017f3c144425e4d623902fd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36755 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.736Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).