Saved in:
Bibliographic Details
Main Authors: Zhang, Yuyao, Huang-Menders, Alexander, Tai, Yu-Wing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916020434763776
author Zhang, Yuyao
Huang-Menders, Alexander
Tai, Yu-Wing
author_facet Zhang, Yuyao
Huang-Menders, Alexander
Tai, Yu-Wing
contents High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce HierEdit, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (\textbf{Local-Window MMDiT}) that refines only edited regions within the original high-res image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (\textbf{Inference Acceleration}) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without any specialized high-resolution training data. Extensive experiments demonstrate that HierEdit achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing. Please check our {\href{https://peteryyzhang.github.io/HierEdit-page/}{\textbf{Project Page}}}.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17294
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
Zhang, Yuyao
Huang-Menders, Alexander
Tai, Yu-Wing
Computer Vision and Pattern Recognition
High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches redundantly process the entire image canvas or rely on large-scale high-resolution datasets, resulting in substantial training and inference costs. We introduce HierEdit, a region-aware hierarchical diffusion framework designed for efficient and scalable high-resolution image editing. Our method first performs edits on a low-resolution proxy using an off-the-shelf editing model to generate a reference and to localize the modified regions. A hierarchical local-window diffusion model (\textbf{Local-Window MMDiT}) that refines only edited regions within the original high-res image, while reusing the unaltered regions as conditioning inputs. The low-resolution proxy further provides structural guidance and intermediate denoising supervision (\textbf{Inference Acceleration}) , ensuring consistent global semantics and stable generation without the need for full-resolution attention computation. This targeted and hierarchical design enables fast, high-fidelity editing of images up to 4K resolution without any specialized high-resolution training data. Extensive experiments demonstrate that HierEdit achieves competitive visual quality on commodity-resolution datasets while significantly accelerating inference and extending seamlessly to ultra-high-resolution 4K editing. Please check our {\href{https://peteryyzhang.github.io/HierEdit-page/}{\textbf{Project Page}}}.
title HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.17294