DragNeXt: Rethinking Drag-Based Image Editing
Yuan Zhou, Junbao Zhou, Qingshan Xu, Kesen Zhao, Yuxuan Wang, Hao Fei, Richang Hong, Hanwang Zhang

TL;DR
DragNeXt introduces a novel framework for drag-based image editing by explicitly specifying handle regions and leveraging a latent region optimization approach, significantly improving quality and reducing ambiguity.
Contribution
It redefines DBIE as deformation, rotation, and translation of handle regions, and proposes a unified, progressive optimization framework that outperforms existing methods.
Findings
Outperforms existing DBIE methods on NextBench
Addresses ambiguity by explicit handle specification
Enhances editing quality through progressive guidance
Abstract
Drag-Based Image Editing (DBIE), which allows users to manipulate images by directly dragging objects within them, has recently attracted much attention from the community. However, it faces two key challenges: (\emph{\textcolor{magenta}{i}}) point-based drag is often highly ambiguous and difficult to align with users' intentions; (\emph{\textcolor{magenta}{ii}}) current DBIE methods primarily rely on alternating between motion supervision and point tracking, which is not only cumbersome but also fails to produce high-quality results. These limitations motivate us to explore DBIE from a new perspective -- redefining it as deformation, rotation, and translation of user-specified handle regions. Thereby, by requiring users to explicitly specify both drag areas and types, we can effectively address the ambiguity issue. Furthermore, we propose a simple-yet-effective editing framework,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Computer Graphics and Visualization Techniques · Multimodal Machine Learning Applications
