图像生成

StyleRes: Transforming the Residuals for Real Image Editing with StyleGAN

Hamza Pehlivan, Yusuf Dalva, Aysegul Dundar

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

Leveraging Off-the-shelf Diffusion Model for Multi-attribute Fashion Image Manipulation

Chaerin Kong, DongHyeon Jeon, Ohjoon Kwon, Nojun Kwak

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

Comments Accepted to WACV 2023

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

Katherine Crowson, Stella Biderman, Daniel Kornis, Dashiell Stander, Eric Hallahan, Louis Castricato, Edward Raff

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

Comments Accepted for publication at ECCV 2022 Code available at https://github.com/EleutherAI/vqgan-clip/tree/main/notebooks

PetsGAN: Rethinking Priors for Single Image Generation

Zicheng Zhang, Yinglu Liu, Congying Han, Hailin Shi, Tiande Guo, Bowen Zhou

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

Comments AAAI 2022 (oral)

Optimizing Latent Space Directions For GAN-based Local Image Editing

Ehsan Pajouheshgar, Tong Zhang, Sabine Süsstrunk

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

Comments 4 pages, 5 figures, 1 table

EditGAN: High-Precision Semantic Image Editing

Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, Sanja Fidler

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

Vehicle Image Generation Going Well with The Surroundings

Jeesoo Kim, Jangho Kim, Jaeyoung Yoo, Daesik Kim, Nojun Kwak

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

Towards disease-aware image editing of chest X-rays

Aakash Saboo, Sai Niranjan Ramachandran, Kai Dierkes, Hacer Yalim Keles

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

Learning by Planning: Language-Guided Global Image Editing

Jing Shi, Ning Xu, Yihang Xu, Trung Bui, Franck Dernoncourt, Chenliang Xu

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

Comments Accepted by CVPR2021

Navigating the GAN Parameter Space for Semantic Image Editing

Anton Cherepkov, Andrey Voynov, Artem Babenko

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

Comments Supplementary code: https://github.com/yandex-research/navigan

MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong

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

Comments Accepted by CVPR2021

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls

Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu

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

Comments Accepted by CVPR2021

A Benchmark and Baseline for Language-Driven Image Editing

Jing Shi, Ning Xu, Trung Bui, Franck Dernoncourt, Zheng Wen, Chenliang Xu

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

Comments Accepted by ACCV 2020

In-Domain GAN Inversion for Real Image Editing

Jiapeng Zhu, Yujun Shen, Deli Zhao, Bolei Zhou

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

Comments ECCV 2020 camera-ready

Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software

Satoshi Kosugi, Toshihiko Yamasaki

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

Comments Accepted to AAAI 2020

Bilinear Representation for Language-based Image Editing Using Conditional Generative Adversarial Networks

Xiaofeng Mao, Yuefeng Chen, Yuhong Li, Tao Xiong, Yuan He, Hui Xue

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

Comments To appear at ICASSP 2019. Implementation: https://github.com/vtddggg/BilinearGAN_for_LBIE

FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing

Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu, Wei Liu

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

SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint

Pavel Ostyakov, Roman Suvorov, Elizaveta Logacheva, Oleg Khomenko, Sergey I. Nikolenko

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

Auto-Retoucher(ART) - A framework for Background Replacement and Image Editing

Yunxuan Xiao, Yikai Li, Yuwei Wu, Lizhen Zhu

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

Comments 5 pages, 4 figures

Language-Based Image Editing with Recurrent Attentive Models

Jianbo Chen, Yelong Shen, Jianfeng Gao, Jingjing Liu, Xiaodong Liu

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

Comments Accepted to CVPR 2018 as a Spotlight

Towards Automatic Image Editing: Learning to See another You

Amir Ghodrati, Xu Jia, Marco Pedersoli, Tinne Tuytelaars

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

Qwen-Image-Flash: Beyond Objective Design

Qwen-Image-Flash：超越目标设计

Tianhe Wu, Kun Yan, Zikai Zhou, Lihan Jiang, Jiahao Li, Jie Zhang, Kaiyuan Gao, Ningyuan Tang, Shengming Yin, Xiaoyue Chen, Xiao Xu, Yilei Chen, Yuxiang Chen, Yan Shu, Yixian Xu, Yanran Zhang, Zihao Liu, Zhendong Wang, Zekai Zhang, Deqing Li, Liang Peng, Yi Wang, Jingren Zhou, Chenfei Wu

机构 * alibaba-inc.com（阿里巴巴公司） 纠错

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

AI总结 本文通过系统研究数据组成、教师指导和任务混合三个因素，提出Qwen-Image-Flash，表明有效的少步蒸馏不仅需要精心设计的目标，还需要对更广泛的训练流程进行原则性组织。

SurFITR: A Dataset for Surveillance Image Forgery Detection and Localisation

SurFITR：用于监控图像伪造检测与定位的数据集

Qizhou Wang, Guansong Pang, Christopher Leckie

机构 * The University of Melbourne（墨尔本大学） ； Singapore Management University（新加坡管理大学） 纠错

专题命中 图像编辑 ：image generation(abstract)；image editing(abstract)；image synthesis(abstract)；分类 cs.CV、cs.MM

AI总结 SurFITR数据集旨在解决监控场景中伪造检测与定位的挑战，通过多模态LLM生成大量高质量伪造图像，提升检测模型在不同场景下的性能。

Click2Mask: Local Editing with Dynamic Mask Generation

Omer Regev, Omri Avrahami, Dani Lischinski

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

Comments Accepted to AAAI 2025. Project page is available at https://omeregev.github.io/click2mask/

MIRAGE: Protecting against Malicious Image Editing via False Moderation

MIRAGE: 通过虚假审核保护图像免受恶意编辑

Anshul Nasery, Ramnath Kumar, Cho-Jui Hsieh, Sewoong Oh

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

AI总结 提出MIRAGE方法，通过对抗性扰动使审核分类器将图像标记为违规，从而阻止AI图像编辑，无需模型权重或提示，在商业API上成功率超88%。

PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing

PRIVATEDIT：面向面部生成图像编辑的隐私保护流程

Dipesh Tamboli, Vineet Punyamoorty, Atharv Pawar, Vaneet Aggarwal

机构 * Elmore Family School of Electrical and Computer Engineering, Purdue University（帕克大学埃尔莫尔工程学院） ； National Institute of Standards and Technology（国家标准与技术研究院） ； Rice University（里奇大学） ； Department of Physics, Colorado State University（科罗拉多州立大学物理系） ； Electrical Engineering Department, University of Colorado（科罗拉多大学电气工程系） 纠错

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

AI总结 PRIVATEDIT提出了一种隐私保护的面部生成图像编辑流程，通过设备端分割和遮罩技术实现用户对生物特征数据的控制，无需修改第三方模型，确保隐私安全。

Comments Accepted to IEEE Transactions on Artificial Intelligence, Feb 2026

Style Transfer as Bias Mitigation: Diffusion Models for Synthetic Mental Health Text for Arabic

风格迁移作为偏见缓解：用于阿拉伯语合成心理健康文本的扩散模型

Saad Mankarious, Aya Zirikly

机构 * School of Engineering and Applied Science（工程与应用科学学院） ； George Washington University（乔治·华盛顿大学） 纠错

专题命中 图像编辑 ：diffusion(title,abstract)

AI总结 本文提出基于扩散模型的风格迁移方法，用于生成阿拉伯语心理健康文本，以缓解性别偏见问题。

DiffStyleTS: Diffusion Model for Style Transfer in Time Series

Mayank Nagda, Phil Ostheimer, Justus Arweiler, Indra Jungjohann, Jennifer Werner, Dennis Wagner, Aparna Muraleedharan, Pouya Jafari, Jochen Schmid, Fabian Jirasek, Jakob Burger, Michael Bortz, Hans Hasse, Stephan Mandt, Marius Kloft, Sophie Fellenz

机构 * RPTU Kaiserslautern-Landau（凯斯莱特大学） ； Fraunhofer ITWM（弗劳恩霍夫研究所） ； TU Munich（慕尼黑技术大学） ； University of California（加州大学） 纠错

专题命中 图像编辑 ：diffusion(title,abstract)

Synthesizing Optimal Object Selection Predicates for Image Editing using Lattices

Yang He, Xiaoyu Liu, Yuepeng Wang

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

Comments We identified issues in the experimental results and want to withdraw the paper. We plan to submit an updated version once these issues have been resolved

DiffGED: Computing Graph Edit Distance via Diffusion-based Graph Matching

Wei Huang, Hanchen Wang, Dong Wen, Wenjie Zhang, Ying Zhang, Xuemin Lin

专题命中 图像编辑 ：diffusion(title,abstract)