中文
相关论文

相关论文: FaceChain-SuDe: Building Derived Class to Inherit …

200 篇论文

Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance,…

计算机视觉与模式识别 · 计算机科学 2026-04-10 Shulei Wang , Longhui Wei , Xin He , Jianbo Ouyang , Hui Lu , Zhou Zhao , Qi Tian

Existing literature typically treats style-driven and subject-driven generation as two disjoint tasks: the former prioritizes stylistic similarity, whereas the latter insists on subject consistency, resulting in an apparent antagonism. We…

计算机视觉与模式识别 · 计算机科学 2025-08-27 Shaojin Wu , Mengqi Huang , Yufeng Cheng , Wenxu Wu , Jiahe Tian , Yiming Luo , Fei Ding , Qian He

Subject-driven image generation aims at generating images containing customized subjects, which has recently drawn enormous attention from the research community. However, the previous works cannot precisely control the background and…

计算机视觉与模式识别 · 计算机科学 2023-08-21 Tianle Li , Max Ku , Cong Wei , Wenhu Chen

Existing subject-driven text-to-image generation models suffer from tedious fine-tuning steps and struggle to maintain both text-image alignment and subject fidelity. For generating compositional subjects, it often encounters problems such…

计算机视觉与模式识别 · 计算机科学 2025-09-10 Shengyuan Liu , Bo Wang , Ye Ma , Te Yang , Xipeng Cao , Quan Chen , Han Li , Di Dong , Peng Jiang

In the field of human-centric personalized image generation, the adapter-based method obtains the ability to customize and generate portraits by text-to-image training on facial data. This allows for identity-preserved personalization…

计算机视觉与模式识别 · 计算机科学 2024-10-28 Cheng Yu , Haoyu Xie , Lei Shang , Yang Liu , Jun Dan , Liefeng Bo , Baigui Sun

Recent research in subject-driven generation increasingly emphasizes the importance of selective subject features. Nevertheless, accurately selecting the content in a given reference image still poses challenges, especially when selecting…

计算机视觉与模式识别 · 计算机科学 2025-01-07 Junjie Hu , Shuyong Gao , Lingyi Hong , Qishan Wang , Yuzhou Zhao , Yan Wang , Wenqiang Zhang

Recent advancement in personalized image generation have unveiled the intriguing capability of pre-trained text-to-image models on learning identity information from a collection of portrait images. However, existing solutions are…

Recently customized generation has significant potential, which uses as few as 3-5 user-provided images to train a model to synthesize new images of a specified subject. Though subsequent applications enhance the flexibility and diversity…

计算机视觉与模式识别 · 计算机科学 2024-07-15 Tianchu Guo , Pengyu Li , Biao Wang , Xiansheng Hua

Current 3D/4D generation methods are usually optimized for photorealism, efficiency, and aesthetics. However, they often fail to preserve the semantic identity of the subject across different viewpoints. Adapting generation methods with one…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Shuhong Zheng , Ashkan Mirzaei , Igor Gilitschenski

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples. However, this…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Wenhu Chen , Hexiang Hu , Yandong Li , Nataniel Ruiz , Xuhui Jia , Ming-Wei Chang , William W. Cohen

Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject when inputs contain multiple candidates. This limitation…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Yuran Wang , Bohan Zeng , Chengzhuo Tong , Wenxuan Liu , Yang Shi , Xiaochen Ma , Hao Liang , Yuanxing Zhang , Wentao Zhang

Personalized image generation aims to faithfully preserve a reference subject's identity while adapting to diverse text prompts. Existing optimization-based methods ensure high fidelity but are computationally expensive, while…

图形学 · 计算机科学 2025-10-10 Yongzhi Li , Saining Zhang , Yibing Chen , Boying Li , Yanxin Zhang , Xiaoyu Du

Object recognition has become a crucial part of machine learning and computer vision recently. The current approach to object recognition involves Deep Learning and uses Convolutional Neural Networks to learn the pixel patterns of the…

计算机视觉与模式识别 · 计算机科学 2017-08-29 Abrar Ahmed , Anish Bikmal

Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Sangwon Jang , Jaehyeong Jo , Kimin Lee , Sung Ju Hwang

Generating customized content in videos has received increasing attention recently. However, existing works primarily focus on customized text-to-video generation for single subject, suffering from subject-missing and attribute-binding…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Hong Chen , Xin Wang , Yipeng Zhang , Yuwei Zhou , Zeyang Zhang , Siao Tang , Wenwu Zhu

Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a…

计算机视觉与模式识别 · 计算机科学 2023-03-16 Nataniel Ruiz , Yuanzhen Li , Varun Jampani , Yael Pritch , Michael Rubinstein , Kfir Aberman

The Federated Domain Generalization for Person re-identification (FedDG-ReID) aims to learn a global server model that can be effectively generalized to source and target domains through distributed source domain data. Existing methods…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Xin Xu , Chaoyue Ren , Wei Liu , Wenke Huang , Bin Yang , Zhixi Yu , Kui Jiang

This paper introduces a tuning-free method for both object insertion and subject-driven generation. The task involves composing an object, given multiple views, into a scene specified by either an image or text. Existing methods struggle to…

计算机视觉与模式识别 · 计算机科学 2024-12-12 Daniel Winter , Asaf Shul , Matan Cohen , Dana Berman , Yael Pritch , Alex Rav-Acha , Yedid Hoshen

Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge. In this work, we consider few-shot classification, and aim to shed light on what makes some novel classes easier…

Current subject-driven image generation methods encounter significant challenges in person-centric image generation. The reason is that they learn the semantic scene and person generation by fine-tuning a common pre-trained diffusion, which…

计算机视觉与模式识别 · 计算机科学 2024-05-06 Yibin Wang , Weizhong Zhang , Jianwei Zheng , Cheng Jin
‹ 上一页 1 2 3 10 下一页 ›