图像生成

Structure-Preserving Zero-Shot Image Editing via Stage-Wise Latent Injection in Diffusion Models

Dasol Jeong, Donggoo Kang, Jiwon Park, Hyebean Lee, Joonki Paik

机构 * Department of Image（图像系） ； Department of Artificial Intelligence（人工智能系） 纠错

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion

Zechao Zhan, Dehong Gao, Jinxia Zhang, Jiale Huang, Yang Hu, Xin Wang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

GeoDiffuser: Geometry-Based Image Editing with Diffusion Models

Rahul Sajnani, Jeroen Vanbaar, Jie Min, Kapil Katyal, Srinath Sridhar

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Accepted to WACV 2025, Tucson, Arizona, USA. For project page, see https://ivl.cs.brown.edu/research/geodiffuser.html

AdaptiveDrag: Semantic-Driven Dragging on Diffusion-Based Image Editing

DuoSheng Chen, Binghui Chen, Yifeng Geng, Liefeng Bo

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing

Naufal Suryanto, Andro Aprila Adiputra, Ahmada Yusril Kadiptya, Thi-Thu-Huong Le, Derry Pratama, Yongsu Kim, Howon Kim

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments 19 pages, under review, code and dataset will be available at https://github.com/naufalso/cityscape-adverse

Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing

Haonan Lin, Mengmeng Wang, Jiahao Wang, Wenbin An, Yan Chen, Yong Liu, Feng Tian, Guang Dai, Jingdong Wang, Qianying Wang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Accepted in NeurIPS 2024

ERDDCI: Exact Reversible Diffusion via Dual-Chain Inversion for High-Quality Image Editing

Jimin Dai, Yingzhen Zhang, Shuo Chen, Jian Yang, Lei Luo

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM

Stefan Stefanache, Lluís Pastor Pérez, Julen Costa Watanabe, Ernesto Sanchez Tejedor, Thomas Hofmann, Enis Simsar

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments 35 pages (17 main paper, 18 appendix), 22 figures

InverseMeetInsert: Robust Real Image Editing via Geometric Accumulation Inversion in Guided Diffusion Models

Yan Zheng, Lemeng Wu

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments 8 pages, 6 figures

FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuning

Zhi Chen, Zecheng Zhao, Yadan Luo, Zi Huang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Technical Report

InstructRL4Pix: Training Diffusion for Image Editing by Reinforcement Learning

Tiancheng Li, Jinxiu Liu, Huajun Chen, Qi Liu

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing

Yujun Shi, Chuhui Xue, Jun Hao Liew, Jiachun Pan, Hanshu Yan, Wenqing Zhang, Vincent Y. F. Tan, Song Bai

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Code is released at https://github.com/Yujun-Shi/DragDiffusion

RotationDrag: Point-based Image Editing with Rotated Diffusion Features

Minxing Luo, Wentao Cheng, Jian Yang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Code is released at https://github.com/Tony-Lowe/RotationDrag

SketchFFusion: Sketch-guided image editing with diffusion model

Weihang Mao, Bo Han, Zihao Wang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments work in progress

Iterative Multi-granular Image Editing using Diffusion Models

K J Joseph, Prateksha Udhayanan, Tripti Shukla, Aishwarya Agarwal, Srikrishna Karanam, Koustava Goswami, Balaji Vasan Srinivasan

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title)；image synthesis(abstract)；分类 cs.CV

Comments Accepted to IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024

EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods

Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, Shell Xu Hu, Soheil Feizi

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Effective Real Image Editing with Accelerated Iterative Diffusion Inversion

Zhihong Pan, Riccardo Gherardi, Xiufeng Xie, Stephen Huang

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Accepted to ICCV 2023 (Oral)

Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models

Naoki Matsunaga, Masato Ishii, Akio Hayakawa, Kenji Suzuki, Takuya Narihira

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Accepted by AI for Content Creation (AI4CC) workshop at CVPR 2023

InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions

Qian Wang, Biao Zhang, Michael Birsak, Peter Wonka

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Project page: https://qianwangx.github.io/InstructEdit/

Paint by Example: Exemplar-based Image Editing with Diffusion Models

Binxin Yang, Shuyang Gu, Bo Zhang, Ting Zhang, Xuejin Chen, Xiaoyan Sun, Dong Chen, Fang Wen

专题命中 图像编辑 ：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Code: https://github.com/Fantasy-Studio/Paint-by-Example

SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder

Ronen Kamenetsky, Sara Dorfman, Daniel Garibi, Roni Paiss, Or Patashnik, Daniel Cohen-Or

机构 * Tel Aviv University（特拉维夫大学） ； Google DeepMind（谷歌DeepMind） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；text-to-image(abstract)；diffusion(abstract)；image synthesis(abstract)

Comments Project page at: https://ronen94.github.io/SAEdit/

Inversion-Based Style Transfer with Diffusion Models

Yuxin Zhang, Nisha Huang, Fan Tang, Haibin Huang, Chongyang Ma, Weiming Dong, Changsheng Xu

专题命中 图像编辑 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)；image synthesis(abstract)

Comments accepted by CVPR 2023

Imagine Before You Draw: Visual Prompt Engineering for Image Generation

先构思再绘制：面向图像生成的视觉提示工程

Liyu Jia, Fengda Zhang, Jiachun Pan, Kesen Zhao, Saining Zhang, Wang Lin, Weijia Wu, Yue Liao, Aojun Zhou, Hanwang Zhang

机构 * Nanyang Technological University（南洋理工大学） ； National University of Singapore（国立新加坡大学） ； Zhejiang University（浙江大学） ； The Chinese University of Hong Kong（香港中文大学） 纠错

专题命中 图像编辑 ：image generation(title,abstract)；text-to-image(abstract)；diffusion(abstract)；image editing(abstract)

AI总结 提出视觉提示工程（VPE），通过在单一模型内先生成视觉语义令牌作为中间计划，再生成完整图像，从而避免信息瓶颈，提升图像生成质量与编辑保真度。

Instruction-based Image Editing with Planning, Reasoning, and Generation

基于指令的图像编辑与规划、推理和生成

Liya Ji, Chenyang Qi, Qifeng Chen

机构 * HKUST（香港科技大学） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

AI总结 本文提出一种多模态模型，通过链式思考规划、编辑区域推理和编辑，提升基于指令的图像编辑能力，以应对更复杂的真实场景。

Comments 10 pages, 7 figures

Journal ref Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025, Page 17506--17515

LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing

LAMS-Edit: 基于调度器的潜在与注意力混合用于改进扩散模型图像和风格编辑中的内容保留

Wingwa Fu, Takayuki Okatani

机构 * Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究生院） 纠错

专题命中 图像编辑 ：diffusion(title,abstract)；image generation(abstract)；text-to-image(abstract)；image editing(abstract)

AI总结 LAMS-Edit通过调度器结合潜在表示和注意力图，实现扩散模型中更精确的内容保留与编辑应用，支持区域掩码编辑和风格迁移。

Discrete Noise Inversion for Next-scale Autoregressive Text-based Image Editing

Quan Dao, Xiaoxiao He, Ligong Han, Ngan Hoai Nguyen, Amin Heyrani Nobar, Faez Ahmed, Han Zhang, Viet Anh Nguyen, Dimitris Metaxas

机构 * Rutgers University（罗格斯大学） ； Red Hat AI Innovation（红帽AI创新） ； MIT（麻省理工学院） ； ReveAI ； CUHK（香港中文大学） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

Comments update affiliation

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

Taihang Hu, Linxuan Li, Kai Wang, Yaxing Wang, Jian Yang, Ming-Ming Cheng

机构 * VCIP, College of Computer Science, Nankai University（VCIP，计算机科学学院，南开大学） ； NKIARI, Shenzhen Futian（NKIARI，深圳福田） ； Computer Vision Center, Universitat Autònoma de Barcelona（计算机视觉中心，巴塞罗那自治大学） ； City University of Hong Kong (Dongguan)（香港城市大学（东莞）） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

Comments Accepted by ICCV2025. Code will be released in https://github.com/hutaiHang/ATM

Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing

Joowon Kim, Ziseok Lee, Donghyeon Cho, Sanghyun Jo, Yeonsung Jung, Kyungsu Kim, Eunho Yang

机构 * KAIST（韩国科学技术院） ； Seoul National University（首尔国立大学） ； OGQ 纠错

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

Comments Accepted to ICCV 2025

Don't Forget your Inverse DDIM for Image Editing

Guillermo Gomez-Trenado, Pablo Mesejo, Oscar Cordón, Stéphane Lathuilière

机构 * University of Granada and DaSCI Research Institute（格拉纳达大学和DaSCI研究机构） ； Panacea Cooperative Research（Panacea合作研究） ； Inria at University Grenoble Alpes（Grenoble Alpes大学的Inria） 纠错

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

Comments 12 pages, 12 figures, code available at https://guillermogotre.github.io/sage/

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

Tianyi Wei, Yifan Zhou, Dongdong Chen, Xingang Pan

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；diffusion(abstract)

Comments Project page: https://wtybest.github.io/projects/FreeFlux/