图像生成

Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation

Yunnan Wang, Ziqiang Li, Zequn Zhang, Wenyao Zhang, Baao Xie, Xihui Liu, Wenjun Zeng, Xin Jin

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

Comments Accepted by NeurlPS 2024

ControlEdit: A MultiModal Local Clothing Image Editing Method

Di Cheng, YingJie Shi, ShiXin Sun, JiaFu Zhang, WeiJing Wang, Yu Liu

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

MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance

Debin Meng, Christos Tzelepis, Ioannis Patras, Georgios Tzimiropoulos

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

Comments Accepted at ECCV 2024 AIM workshop

EditWorld: Simulating World Dynamics for Instruction-Following Image Editing

Ling Yang, Bohan Zeng, Jiaming Liu, Hong Li, Minghao Xu, Wentao Zhang, Shuicheng Yan

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

Comments Project: https://github.com/YangLing0818/EditWorld

TIE: Revolutionizing Text-based Image Editing for Complex-Prompt Following and High-Fidelity Editing

Xinyu Zhang, Mengxue Kang, Fei Wei, Shuang Xu, Yuhe Liu, Lin Ma

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

LocInv: Localization-aware Inversion for Text-Guided Image Editing

Chuanming Tang, Kai Wang, Fei Yang, Joost van de Weijer

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

Comments Accepted by CVPR 2024 Workshop AI4CC

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

Yuxi Ren, Jie Wu, Yanzuo Lu, Huafeng Kuang, Xin Xia, Xionghui Wang, Qianqian Wang, Yixing Zhu, Pan Xie, Shiyin Wang, Xuefeng Xiao, Yitong Wang, Min Zheng, Lean Fu

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

Text-Driven Image Editing via Learnable Regions

Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Lu Jiang, Ming-Hsuan Yang

专题命中 图像编辑 ：image editing(title,abstract)；image generation(abstract)；text-to-image(abstract)；分类 cs.CV

Comments Accepted to CVPR 2024 Project webpage: https://yuanze-lin.me/LearnableRegions_page

Noise Map Guidance: Inversion with Spatial Context for Real Image Editing

Hansam Cho, Jonghyun Lee, Seoung Bum Kim, Tae-Hyun Oh, Yonghyun Jeong

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

Comments ICLR 2024

MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance

Qi Mao, Lan Chen, Yuchao Gu, Zhen Fang, Mike Zheng Shou

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

Comments for project page, see https://mag-edit.github.io/

Learning to Follow Object-Centric Image Editing Instructions Faithfully

Tuhin Chakrabarty, Kanishk Singh, Arkadiy Saakyan, Smaranda Muresan

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

Comments Findings of EMNLP 2023 (Long paper)

Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

Kai Wang, Fei Yang, Shiqi Yang, Muhammad Atif Butt, Joost van de Weijer

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

Comments Neurips 2023. The code page: https://github.com/wangkai930418/DPL

Visual Instruction Inversion: Image Editing via Visual Prompting

Thao Nguyen, Yuheng Li, Utkarsh Ojha, Yong Jae Lee

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

Comments Project page: https://thaoshibe.github.io/visii/

Designing a Better Asymmetric VQGAN for StableDiffusion

Zixin Zhu, Xuelu Feng, Dongdong Chen, Jianmin Bao, Le Wang, Yinpeng Chen, Lu Yuan, Gang Hua

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

Comments code is available at https://github.com/buxiangzhiren/Asymmetric_VQGAN

Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing

Edit-R2：面向多轮图像编辑的上下文感知强化学习

Yuxiao Ye, Haoran He, Fangyuan Kong, Xintao Wang, Pengfei Wan, Kun Gai, Ling Pan

机构 * Hong Kong University of Science and Technology（香港理工大学） ； Kuaishou Technology（快手科技） 纠错

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

AI总结 提出Edit-R2框架，通过重构会话意图和联合优化推理与生成的强化学习，解决多轮图像编辑中的长上下文稀释和状态污染问题，并在MICE-Bench基准上取得领先性能。

On the Controllability-Fidelity Frontier in Diffusion Editing

扩散编辑中的可控性-保真度前沿

Yi Hu, Leying Yi, Emily Davis, Finn Carter

机构 * Xidian University（西安电子科技大学） 纠错

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

AI总结 本文理论结合实证研究扩散图像编辑中用户意图遵循、非目标内容保持与输出质量间的权衡，提出算法框架并揭示关键失败模式，讨论伦理考量。

Comments Preprint

DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation

Yipeng Leng, Qiangjuan Huang, Zhiyuan Wang, Yangyang Liu, Haoyu Zhang

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

SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow

Kenan Tang, Yanhong Li, Yao Qin

机构 * University of California, Santa Barbara（加州大学圣芭芭拉分校） 纠错

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

Comments The paper has been accepted to NeurIPS Creative AI Track 2025. Figure 4(c) has been accepted to CVPR AI Art Gallery 2025

Stable Flow: Vital Layers for Training-Free Image Editing

Omri Avrahami, Or Patashnik, Ohad Fried, Egor Nemchinov, Kfir Aberman, Dani Lischinski, Daniel Cohen-Or

机构 * Snap Research ； The Hebrew University of Jerusalem（耶路撒冷希伯来大学） ； Tel Aviv University（特拉维夫大学） ； Reichman University（里赫曼大学） 纠错

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

Comments CVPR 2025. Project page is available at https://omriavrahami.com/stable-flow

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

Wenxuan Wang, Kuiyi Gao, Youliang Yuan, Jen-tse Huang, Qiuzhi Liu, Shuai Wang, Wenxiang Jiao, Zhaopeng Tu

机构 * Renmin University of China（中国人民大学） ； Chinese University of Hong Kong（香港大学） ； Chinese University of Hong Kong, Shenzhen（香港大学（深圳）） ； Johns Hopkins University（约翰霍普金斯大学） ； Tencent（腾讯） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

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

Comments Accepted by ACL 2025 Findings

Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation

Fulvio Sanguigni, Davide Morelli, Marcella Cornia, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； University of Pisa（比萨大学） 纠错

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

Comments IJCNN 2025

New Job, New Gender? Measuring the Social Bias in Image Generation Models

Wenxuan Wang, Haonan Bai, Jen-tse Huang, Yuxuan Wan, Youliang Yuan, Haoyi Qiu, Nanyun Peng, Michael R. Lyu

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

Comments ACM MM 2024 Oral

Prompt-to-Prompt Image Editing with Cross Attention Control

Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or

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

Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networks

Chen Zhang, Yinghao Xu, Yujun Shen

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

Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications

基于指令的图像编辑：数据、模型、评估及应用综述

Xianghao Zang, Zijian Jiang, Jiarong Cheng, Qianrui Teng, Ying He, Yuxuan Mu, Chao Ban, Huayu Zhang, Lanxiang Zhou, Zerun Feng, Chi Zhang

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

AI总结 综述基于指令的图像编辑研究，围绕任务定义、数据构建、模型架构、评估指标及商业应用五个维度展开，提出综合深度诊断基准，通过开源方案比较揭示优缺点，探讨未来研究方向以推动该领域发展。

Comments 33 pages, 7 figures, Vicinagearth

Journal ref Zang, X., Jiang, Z., Cheng, J. et al. Instruction-based image editing: a survey on data, models, evaluation, and applications. Vicinagearth 3, 3 (2026)

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing

MotionEdit: 动作导向图像编辑的基准测试与学习

Yixin Wan, Lei Ke, Wenhao Yu, Kai-Wei Chang, Dong Yu

机构 * Tencent AI（腾讯AI） ； University of California, Los Angeles（加州大学洛杉矶分校） 纠错

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

AI总结 MotionEdit提出一个动作导向图像编辑数据集及评估基准，通过MotionNFT框架提升编辑质量和运动保真度。

Comments Technical Report. We propose MotionEdit, a dataset and benchmark for motion-centric image editing. We also introduce MotionNFT, a reward training framework to improve existing models with motion-aware guidance. Github: https://github.com/elainew728/motion-edit/

EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing

EditBridge：迈向忠实且高效的超高清图像编辑

Jiayi Song, Shijie Huang, Fangtai Wu, Yubo Huang, Zhenxiong Tan, Songhua Liu, Jiaming Liu, Ruihua Huang

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院） ； Qwen Business Unit of Alibaba（阿里巴巴通义千问业务部） ； National University of Singapore（新加坡国立大学） 纠错

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

AI总结 针对现有扩散图像编辑模型无法高效处理超高清图像的问题，提出EditBridge扩散桥框架，通过先验引导的块级稀疏注意力机制实现4K高保真编辑，速度提升显著。

Qwen-Video-Edit: Instruction-Based Video Editing by Repurposing an Image Editing Model

Qwen-Video-Edit：通过复用图像编辑模型实现基于指令的视频编辑

Yunpeng Bai, Yossi Gandelsman, Michaël Gharbi, Qixing Huang

机构 * UT Austin（德克萨斯大学奥斯汀分校） ； Reve（Reve公司） 纠错

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

AI总结 该研究提出Qwen-Video-Edit，通过复用Qwen-Image-Edit图像编辑模型，经少量适配实现基于指令的视频编辑，证明图像编辑先验可迁移至视频编辑任务。

Comments Project Page: https://yunpeng1998.github.io/Qwen-Video-Edit-Page Code: https://github.com/yunpeng1998/Qwen-Video-Edit Model: https://huggingface.co/yunpeng1998/Qwen-Video-Edit

Training-Free Multi-Concept Image Editing

无需训练的多概念图像编辑

Niki Foteinopoulou, Ignas Budvytis, Stephan Liwicki

机构 * Cambridge Research Laboratory, Toshiba Europe（东芝欧洲剑桥研究实验室） 纠错

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

AI总结 提出无需训练的多概念图像编辑方法，通过概念蒸馏采样实现多视觉概念的无缝组合与控制，提升图像编辑的精度与细节表现。

Comments Accepted in ECCV'26 (17 pages, 13 figures)

PosBridge: Multi-View Positional Embedding Transplant for Identity-Aware Image Editing

PosBridge：用于身份感知图像编辑的多视图位置嵌入迁移

Peilin Xiong, Junwen Chen, Honghui Yuan, Keiji Yanai

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

AI总结 PosBridge是一种高效灵活的图像编辑框架，通过位置嵌入迁移与角点居中布局，实现自定义对象的无缝插入，在结构一致性、保真度和效率上优于主流基线。