中文
相关论文

相关论文: AnyPhoto: Multi-Person Identity Preserving Image G…

200 篇论文

Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Hengyuan Xu , Wei Cheng , Peng Xing , Yixiao Fang , Shuhan Wu , Rui Wang , Xianfang Zeng , Daxin Jiang , Gang Yu , Xingjun Ma , Yu-Gang Jiang

Recent advancements in image-conditioned image generation have demonstrated substantial progress. However, foreground-conditioned image generation remains underexplored, encountering challenges such as compromised object integrity,…

计算机视觉与模式识别 · 计算机科学 2025-02-25 Tianyidan Xie , Rui Ma , Qian Wang , Xiaoqian Ye , Feixuan Liu , Ying Tai , Zhenyu Zhang , Lanjun Wang , Zili Yi

This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch. Traditional methods, such as Textual Inversion and…

计算机视觉与模式识别 · 计算机科学 2023-12-07 Yuxuan Yan , Chi Zhang , Rui Wang , Yichao Zhou , Gege Zhang , Pei Cheng , Gang Yu , Bin Fu

Multi-ID customization is an interesting topic in computer vision and attracts considerable attention recently. Given the ID images of multiple individuals, its purpose is to generate a customized image that seamlessly integrates them while…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Jiawei Lin , Guanlong Jiao , Jianjin Xu

Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character reference encoding becomes more susceptible to latent identity…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Zhenyu Xie , Ji Xia , Michael Kampffmeyer , Panwen Hu , Zehua Ma , Yujian Zheng , Jing Wang , Zheng Chong , Xujie Zhang , Xianhang Cheng , Xiaodan Liang , Hao Li

Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing methods are typically designed and optimized for a single…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Jiahao Wang , Hualian Sheng , Sijia Cai , Yuxiao Yang , Weizhan Zhang , Caixia Yan , Bing Deng , Jieping Ye

Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Bin Hu , Zipeng Qi , Guoxi Huang , Zunnan Xu , Ruicheng Zhang , Chongjie Ye , Jun Zhou , Xiu Li , Jingdong Wang

Text-to-image generation for personalized identities aims at incorporating the specific identity into images using a text prompt and an identity image. Based on the powerful generative capabilities of DDPMs, many previous works adopt…

计算机视觉与模式识别 · 计算机科学 2025-05-13 Jinyu Gu , Haipeng Liu , Meng Wang , Yang Wang

In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly trained jointly with base diffusion models, which suffer…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Sergey Karpukhin , Vadim Titov , Andrey Kuznetsov , Aibek Alanov

There has been significant progress in personalized image synthesis with methods such as Textual Inversion, DreamBooth, and LoRA. Yet, their real-world applicability is hindered by high storage demands, lengthy fine-tuning processes, and…

计算机视觉与模式识别 · 计算机科学 2024-02-05 Qixun Wang , Xu Bai , Haofan Wang , Zekui Qin , Anthony Chen , Huaxia Li , Xu Tang , Yao Hu

Facial appearance editing is crucial for digital avatars, AR/VR, and personalized content creation, driving realistic user experiences. However, preserving identity with generative models is challenging, especially in scenarios with limited…

计算机视觉与模式识别 · 计算机科学 2025-03-10 MD Wahiduzzaman Khan , Mingshan Jia , Xiaolin Zhang , En Yu , Caifeng Shan , Kaska Musial-Gabrys

Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image. However,…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Yi Wu , Ziqiang Li , Heliang Zheng , Chaoyue Wang , Bin Li

This work presents FlashFace, a practical tool with which users can easily personalize their own photos on the fly by providing one or a few reference face images and a text prompt. Our approach is distinguishable from existing human photo…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Shilong Zhang , Lianghua Huang , Xi Chen , Yifei Zhang , Zhi-Fan Wu , Yutong Feng , Wei Wang , Yujun Shen , Yu Liu , Ping Luo

We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our method treats identity and text as a unified conditioning…

计算机视觉与模式识别 · 计算机科学 2025-05-23 Zichuan Liu , Liming Jiang , Qing Yan , Yumin Jia , Hao Kang , Xin Lu

Recent advances in large pretrained text-to-image models have shown unprecedented capabilities for high-quality human-centric generation, however, customizing face identity is still an intractable problem. Existing methods cannot ensure…

计算机视觉与模式识别 · 计算机科学 2024-01-30 Qinghe Wang , Xu Jia , Xiaomin Li , Taiqing Li , Liqian Ma , Yunzhi Zhuge , Huchuan Lu

Recent advancements in personalized image generation using diffusion models have been noteworthy. However, existing methods suffer from inefficiencies due to the requirement for subject-specific fine-tuning. This computationally intensive…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Xu Peng , Junwei Zhu , Boyuan Jiang , Ying Tai , Donghao Luo , Jiangning Zhang , Wei Lin , Taisong Jin , Chengjie Wang , Rongrong Ji

Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Siying Cui , Jia Guo , Xiang An , Jiankang Deng , Yongle Zhao , Xinyu Wei , Ziyong Feng

Recent advances in garment-centric image generation from text and image prompts based on diffusion models are impressive. However, existing methods lack support for various combinations of attire, and struggle to preserve the garment…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Xinghui Li , Qichao Sun , Pengze Zhang , Fulong Ye , Zhichao Liao , Wanquan Feng , Songtao Zhao , Qian He

Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video generation, they often face challenges due to the high costs of diverse multi-person…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Zhizhou Zhong , Yicheng Ji , Zhe Kong , Yiying Liu , Jiarui Wang , Jiasun Feng , Lupeng Liu , Xiangyi Wang , Yanjia Li , Yuqing She , Ying Qin , Huan Li , Shuiyang Mao , Wei Liu , Wenhan Luo

Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain with very few samples (fewer than 10), known as few-shot…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Yeqi He , Liang Li , Jiehua Zhang , Yaoqi Sun , Xichun Sheng , Zhidong Zhao , Chenggang Yan
‹ 上一页 1 2 3 10 下一页 ›