图像生成

Zero-Shot Personalization of Objects via Textual Inversion

通过文本逆向实现对象的零样本个性化

Aniket Roy, Maitreya Suin, Rama Chellappa

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Samsung AI Center Toronto（三星AI中心多伦多） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

AI总结 本文提出一种新框架，通过学习网络预测对象特定的文本逆向嵌入，实现快速零样本对象个性化，适用于多种任务和场景。

FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization

FaceSnap: 增强的ID保真网络用于无调优的人像定制

Benxiang Zhai, Yifang Xu, Guofeng Zhang, Yang Li, Sidan Du

机构 * Vision AI System Lab, Nanjing University, Nanjing, China（南京大学视觉人工智能系统实验室） ； Research and Development Department, Wonxing Technology, Shanghai, China（Wonxing技术有限公司研发部） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

AI总结 FaceSnap通过引入面部属性混合器和地标预测器，实现无需微调的高保真人像定制生成。

Comments Accept by ICANN 2025

Can Generative Models Actually Forge Realistic Identity Documents?

生成模型真的能伪造逼真的身份文件吗？

Alexander Vinogradov

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

AI总结 本文研究了生成模型伪造身份文件的能力，发现其在结构真实性上不足，强调跨领域合作的重要性。

Comments 11 pages, 16 figures

Sell It Before You Make It: Revolutionizing E-Commerce with Personalized AI-Generated Items

在制作之前就出售它：通过个性化AI生成物品革新电子商务

Jianghao Lin, Peng Du, Jiaqi Liu, Weite Li, Yong Yu, Weinan Zhang, Yang Cao

机构 * Antai College of Economics and Management（经济管理学院） ； Shanghai Jiao Tong University（上海交通大学） ； Alibaba Group（阿里巴巴集团） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

AI总结 本文提出PerFusion框架，通过个性化AI生成物品提升电子商务的点击率和转化率，同时降低退货率。

Comments Accepted by KDD 2026 ADS Track

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences

Hyojin Bahng, Caroline Chan, Fredo Durand, Phillip Isola

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

Abdelrahman Eldesokey, Aleksandar Cvejic, Bernard Ghanem, Peter Wonka

机构 * KAUST, Saudi Arabia（卡士大学） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

Comments NeurIPS 2025 (Spotlight). Project Page: https://abdo-eldesokey.github.io/mind-the-glitch/

DIVE: Taming DINO for Subject-Driven Video Editing

Yi Huang, Wei Xiong, He Zhang, Chaoqi Chen, Jianzhuang Liu, Mingfu Yan, Shifeng Chen

机构 * Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院） ； vivo AI Lab（vivo AI实验室） ； NVIDIA ； Adobe Research（Adobe研究院） ； Shenzhen University（深圳大学） ； Southeast University（东南大学） ； Shenzhen University of Advanced Technology（深圳大学先进技术学院） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability

Xirui Hu, Jiahao Wang, Hao Chen, Weizhan Zhang, Benqi Wang, Yikun Li, Haishun Nan

机构 * Xi’an Jiaotong University（西安交通大学） ； Film AI Lab, Western Movie Group（西方电影集团影视人工智能实验室） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；personalized generation(abstract)；分类 cs.CV

Comments ICCV 2025

Generating Synthetic Data via Augmentations for Improved Facial Resemblance in DreamBooth and InstantID

Koray Ulusan, Benjamin Kiefer

机构 * University of Tuebingen（图宾根大学） ； LOOKOUT University of Tuebingen（LOOKOUT 图宾根大学） 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted to CVPR 2025 Workshop "Synthetic Data for Computer Vision Workshop", https://syndata4cv.github.io/ Revised version

Latent Space Consistency for Sparse-View CT Reconstruction

Duoyou Chen, Yunqing Chen, Can Zhang, Zhou Wang, Cheng Chen, Ruoxiu Xiao

机构 * University of Science and Technology Beijing（北京科技大学） 纠错

专题命中 个性化与一致性 ：text-to-image(abstract)；diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

Comments ACMMM2025 Accepted

TaleForge: Interactive Multimodal System for Personalized Story Creation

Minh-Loi Nguyen, Quang-Khai Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le

机构 * 1 University of Science, VNU-HCM, Ho Chi Minh City, Vietnam ； 2 Vietnam National University, Ho Chi Minh City, Vietnam ； 3 Department of Computer Science \ of Dayton Ohio, United States 纠错

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategies

Ada Sawilska, Mateusz Trokielewicz

专题命中 个性化与一致性 ：image generation(abstract)；diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

DreamRelation: Bridging Customization and Relation Generation

Qingyu Shi, Lu Qi, Jianzong Wu, Jinbin Bai, Jingbo Wang, Yunhai Tong, Xiangtai Li

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments CVPR 2025

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation

Shaojin Wu, Mengqi Huang, Wenxu Wu, Yufeng Cheng, Fei Ding, Qian He

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Project page: https://bytedance.github.io/UNO Code and model: https://github.com/bytedance/UNO

Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens

Qingsong Xie, Zhao Zhang, Zhe Huang, Yanhao Zhang, Haonan Lu, Zhenyu Yang

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Bidirectional Consistency Models

Liangchen Li, Jiajun He

专题命中 个性化与一致性 ：diffusion(abstract)；image editing(abstract)；inpainting(abstract)；分类 cs.CV

Comments 39 pages, 27 figures; a shorter version of this paper was acceppted at the ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling

LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation

Farzad Farhadzadeh, Debasmit Das, Shubhankar Borse, Fatih Porikli

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted to ICLR 2025

Dense-Face: Personalized Face Generation Model via Dense Annotation Prediction

Xiao Guo, Manh Tran, Jiaxin Cheng, Xiaoming Liu

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments 15 figures, 5 tables

A LoRA is Worth a Thousand Pictures

Chenxi Liu, Towaki Takikawa, Alec Jacobson

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniques

Mahmut S. Gokmen, Jie Zhang, Ge Wang, Jin Chen, Cody Bumgardner

专题命中 个性化与一致性 ：image generation(abstract)；diffusion(abstract)；inpainting(abstract)；分类 cs.CV

OneActor: Consistent Character Generation via Cluster-Conditioned Guidance

Jiahao Wang, Caixia Yan, Haonan Lin, Weizhan Zhang, Mengmeng Wang, Tieliang Gong, Guang Dai, Hao Sun

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization

Cheng Yu, Haoyu Xie, Lei Shang, Yang Liu, Jun Dan, Liefeng Bo, Baigui Sun

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；inpainting(abstract)；分类 cs.CV

Comments 12 pages, 8 figures

Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection

Yuhang Ma, Wenting Xu, Chaoyi Zhao, Keqiang Sun, Qinfeng Jin, Zeng Zhao, Changjie Fan, Zhipeng Hu

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser

Xing Cui, Zekun Li, Pei Pei Li, Huaibo Huang, Xuannan Liu, Zhaofeng He

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments Accepted by European Conference on Computer Vision (ECCV 2024). Project page: https://cuixing100876.github.io/instastyle.github.io/

MuseumMaker: Continual Style Customization without Catastrophic Forgetting

Chenxi Liu, Gan Sun, Wenqi Liang, Jiahua Dong, Can Qin, Yang Cong

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm

Yi Wu, Ziqiang Li, Heliang Zheng, Chaoyue Wang, Bin Li

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Visual Style Prompting with Swapping Self-Attention

Jaeseok Jeong, Junho Kim, Yunjey Choi, Gayoung Lee, Youngjung Uh

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

DreamTuner: Single Image is Enough for Subject-Driven Generation

Miao Hua, Jiawei Liu, Fei Ding, Wei Liu, Jie Wu, Qian He

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization

Xu Peng, Junwei Zhu, Boyuan Jiang, Ying Tai, Donghao Luo, Jiangning Zhang, Wei Lin, Taisong Jin, Chengjie Wang, Rongrong Ji

专题命中 个性化与一致性 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Few-shot Image Generation via Cross-domain Correspondence

Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A. Efros, Yong Jae Lee, Eli Shechtman, Richard Zhang

专题命中 个性化与一致性 ：image generation(title)；分类 cs.CV、cs.GR

Comments CVPR 2021