DragNeXt: Rethinking Drag-Based Image Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Yuan, Zhou, Junbao, Xu, Qingshan, Zhao, Kesen, Wang, Yuxuan, Fei, Hao, Hong, Richang, Zhang, Hanwang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915751466631168
author Zhou, Yuan
Zhou, Junbao
Xu, Qingshan
Zhao, Kesen
Wang, Yuxuan
Fei, Hao
Hong, Richang
Zhang, Hanwang
author_facet Zhou, Yuan
Zhou, Junbao
Xu, Qingshan
Zhao, Kesen
Wang, Yuxuan
Fei, Hao
Hong, Richang
Zhang, Hanwang
contents 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, dubbed \textcolor{SkyBlue}{\textbf{DragNeXt}}. It unifies DBIE as a Latent Region Optimization (LRO) problem and solves it through Progressive Backward Self-Intervention (PBSI), simplifying the overall procedure of DBIE while further enhancing quality by fully leveraging region-level structure information and progressive guidance from intermediate drag states. We validate \textcolor{SkyBlue}{\textbf{DragNeXt}} on our NextBench, and extensive experiments demonstrate that our proposed method can significantly outperform existing approaches. Code will be released on github.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07611
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DragNeXt: Rethinking Drag-Based Image Editing
Zhou, Yuan
Zhou, Junbao
Xu, Qingshan
Zhao, Kesen
Wang, Yuxuan
Fei, Hao
Hong, Richang
Zhang, Hanwang
Computer Vision and Pattern Recognition
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, dubbed \textcolor{SkyBlue}{\textbf{DragNeXt}}. It unifies DBIE as a Latent Region Optimization (LRO) problem and solves it through Progressive Backward Self-Intervention (PBSI), simplifying the overall procedure of DBIE while further enhancing quality by fully leveraging region-level structure information and progressive guidance from intermediate drag states. We validate \textcolor{SkyBlue}{\textbf{DragNeXt}} on our NextBench, and extensive experiments demonstrate that our proposed method can significantly outperform existing approaches. Code will be released on github.
title DragNeXt: Rethinking Drag-Based Image Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.07611