Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ma, Yongjia, Di, Donglin, Liu, Xuan, Chen, Xiaokai, Fan, Lei, Su, Tonghua, Gao, Yue
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910000341843968
author Ma, Yongjia
Di, Donglin
Liu, Xuan
Chen, Xiaokai
Fan, Lei
Su, Tonghua
Gao, Yue
author_facet Ma, Yongjia
Di, Donglin
Liu, Xuan
Chen, Xiaokai
Fan, Lei
Su, Tonghua
Gao, Yue
contents Rectified flow models have achieved remarkable performance in image and video generation tasks. However, existing numerical solvers face a trade-off between fast sampling and high accuracy solutions, limiting their effectiveness in downstream applications such as reconstruction and editing. To address this challenge, we propose leveraging the Adams Bashforth Moulton (ABM) predictor corrector method to enhance the accuracy of ODE solving in rectified flow models. Specifically, we introduce ABM Solver, which integrates a multi step predictor corrector approach to reduce local truncation errors and employs Adaptive Step Size Adjustment to improve sampling speed. Furthermore, to effectively preserve non edited regions while facilitating semantic modifications, we introduce a Mask Guided Feature Injection module. We estimate self-similarity to generate a spatial mask that differentiates preserved regions from those available for editing. Extensive experiments on multiple high resolution image datasets validate that ABM Solver significantly improves inversion precision and editing quality, outperforming existing solvers without requiring additional training or optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16522
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow
Ma, Yongjia
Di, Donglin
Liu, Xuan
Chen, Xiaokai
Fan, Lei
Su, Tonghua
Gao, Yue
Computer Vision and Pattern Recognition
Rectified flow models have achieved remarkable performance in image and video generation tasks. However, existing numerical solvers face a trade-off between fast sampling and high accuracy solutions, limiting their effectiveness in downstream applications such as reconstruction and editing. To address this challenge, we propose leveraging the Adams Bashforth Moulton (ABM) predictor corrector method to enhance the accuracy of ODE solving in rectified flow models. Specifically, we introduce ABM Solver, which integrates a multi step predictor corrector approach to reduce local truncation errors and employs Adaptive Step Size Adjustment to improve sampling speed. Furthermore, to effectively preserve non edited regions while facilitating semantic modifications, we introduce a Mask Guided Feature Injection module. We estimate self-similarity to generate a spatial mask that differentiates preserved regions from those available for editing. Extensive experiments on multiple high resolution image datasets validate that ABM Solver significantly improves inversion precision and editing quality, outperforming existing solvers without requiring additional training or optimization.
title Adams Bashforth Moulton Solver for Inversion and Editing in Rectified Flow
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16522