R-Genie: Reasoning-Guided Generative Image Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Dong, He, Lingfeng, Yan, Rui, Shen, Fei, Tang, Jinhui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918097990975488
author Zhang, Dong
He, Lingfeng
Yan, Rui
Shen, Fei
Tang, Jinhui
author_facet Zhang, Dong
He, Lingfeng
Yan, Rui
Shen, Fei
Tang, Jinhui
contents While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editing operations, lacking deep comprehension of implicit user intentions and contextual reasoning. In this work, we introduce a new image editing paradigm: reasoning-guided generative editing, which synthesizes images based on complex, multi-faceted textual queries accepting world knowledge and intention inference. To facilitate this task, we first construct a comprehensive dataset featuring over 1,000 image-instruction-edit triples that incorporate rich reasoning contexts and real-world knowledge. We then propose R-Genie: a reasoning-guided generative image editor, which synergizes the generation power of diffusion models with advanced reasoning capabilities of multimodal large language models. R-Genie incorporates a reasoning-attention mechanism to bridge linguistic understanding with visual synthesis, enabling it to handle intricate editing requests involving abstract user intentions and contextual reasoning relations. Extensive experimental results validate that R-Genie can equip diffusion models with advanced reasoning-based editing capabilities, unlocking new potentials for intelligent image synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17768
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle R-Genie: Reasoning-Guided Generative Image Editing
Zhang, Dong
He, Lingfeng
Yan, Rui
Shen, Fei
Tang, Jinhui
Computer Vision and Pattern Recognition
F.2.2, I.2.7
F.2.2; I.2.7
While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editing operations, lacking deep comprehension of implicit user intentions and contextual reasoning. In this work, we introduce a new image editing paradigm: reasoning-guided generative editing, which synthesizes images based on complex, multi-faceted textual queries accepting world knowledge and intention inference. To facilitate this task, we first construct a comprehensive dataset featuring over 1,000 image-instruction-edit triples that incorporate rich reasoning contexts and real-world knowledge. We then propose R-Genie: a reasoning-guided generative image editor, which synergizes the generation power of diffusion models with advanced reasoning capabilities of multimodal large language models. R-Genie incorporates a reasoning-attention mechanism to bridge linguistic understanding with visual synthesis, enabling it to handle intricate editing requests involving abstract user intentions and contextual reasoning relations. Extensive experimental results validate that R-Genie can equip diffusion models with advanced reasoning-based editing capabilities, unlocking new potentials for intelligent image synthesis.
title R-Genie: Reasoning-Guided Generative Image Editing
topic Computer Vision and Pattern Recognition
F.2.2, I.2.7
F.2.2; I.2.7
url https://arxiv.org/abs/2505.17768