NEP: Autoregressive Image Editing via Next Editing Token Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Huimin, Ma, Xiaojian, Zhao, Haozhe, Zhao, Yanpeng, Li, Qing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908586913824768
author Wu, Huimin
Ma, Xiaojian
Zhao, Haozhe
Zhao, Yanpeng
Li, Qing
author_facet Wu, Huimin
Ma, Xiaojian
Zhao, Haozhe
Zhao, Yanpeng
Li, Qing
contents Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as Next Editing-token Prediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner. The project page is: https://nep-bigai.github.io/
format Preprint
id arxiv_https___arxiv_org_abs_2508_06044
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NEP: Autoregressive Image Editing via Next Editing Token Prediction
Wu, Huimin
Ma, Xiaojian
Zhao, Haozhe
Zhao, Yanpeng
Li, Qing
Computer Vision and Pattern Recognition
Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as Next Editing-token Prediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner. The project page is: https://nep-bigai.github.io/
title NEP: Autoregressive Image Editing via Next Editing Token Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.06044