图像生成 - arXivDaily 专题

2510.00006 2025-10-02 cs.SD cs.CL cs.CY cs.MM eess.AS 57%

Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches

Kajwan Ziaoddini

专题命中个性化与一致性：diffusion(abstract)；分类 cs.MM

2412.07754 2025-10-02 cs.CV cs.AI cs.LG 57%

PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation

Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, Josef Kittler

机构 * School of Computer Science and Electronic Engineering, University of Surrey（计算机科学与电子工程系，塞夫顿大学）； Centre for Vision, Speech and Signal Processing, University of Surrey（视觉、语音与信号处理中心，塞夫顿大学）； School of Artificial Intelligence and Computer Science, Jiangnan University（人工智能与计算机科学系，江南大学）

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

2506.03621 2025-10-01 cs.CV cs.AI 57%

Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation

Chaehun Shin, Jooyoung Choi, Johan Barthelemy, Jungbeom Lee, Sungroh Yoon

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

2509.25172 2025-09-30 cs.CV cs.LG 57%

Personalized Vision via Visual In-Context Learning

Yuxin Jiang, Yuchao Gu, Yiren Song, Ivor Tsang, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室）； A*STAR, Singapore（新加坡科技研究局）

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

Comments Project page: https://yuxinn-j.github.io/projects/PICO

2509.24878 2025-09-30 cs.CV cs.RO 57%

ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation

Jiuhong Xiao, Roshan Nayak, Ning Zhang, Daniel Tortei, Giuseppe Loianno

机构 * New York University（纽约大学）； Technology Innovation Institute（技术创新研究所）； University of California, Berkeley（加州大学伯克利分校）

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

Comments 23 pages including the checklist and appendix. Accepted at NeurIPS 2025

2509.23878 2025-09-30 cs.SD cs.AI cs.MM eess.AS 57%

Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription

Wei Zeng, Junchuan Zhao, Ye Wang

机构 * National University of Singapore（新加坡国立大学）

专题命中个性化与一致性：diffusion(abstract)；分类 cs.MM

Comments 30 pages, 13 figures

2509.10678 2025-09-30 cs.GR 57%

T2Bs: Text-to-Character Blendshapes via Video Generation

Jiahao Luo, Chaoyang Wang, Michael Vasilkovsky, Vladislav Shakhrai, Di Liu, Peiye Zhuang, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee, James Davis, Jian Wang

专题命中个性化与一致性：diffusion(abstract)；分类 cs.GR

2509.18602 2025-09-24 cs.CV 57%

Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

Xu Liu, Yibo Lu, Xinxian Wang, Xinyu Wu

机构 * University of Washington, Seattle, WA 98195, USA（华盛顿大学）； Nanjing University of Posts and Telecommunications, Jiangsu, Nanjing, China（南京邮电大学）； Nanjing Foreign Language School, Jiangsu, Nanjing, China（南京外国语学校）

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

Comments Accepted at ACPR 2025 (oral)

2509.16064 2025-09-22 cs.GR 57%

Generating Detailed Character Motion from Blocking Poses

Purvi Goel, Guy Tevet, C. K. Liu, Kayvon Fatahalian

专题命中个性化与一致性：diffusion(abstract)；分类 cs.GR

2509.15496 2025-09-22 cs.CV 57%

Lynx: Towards High-Fidelity Personalized Video Generation

Shen Sang, Tiancheng Zhi, Tianpei Gu, Jing Liu, Linjie Luo

机构 * ByteDance（字节跳动）

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

Comments Lynx Technical Report

2509.12001 2025-09-16 eess.IV cs.CV 57%

Data-driven Smile Design: Personalized Dental Aesthetics Outcomes Using Deep Learning

Marcus Lin, Jennifer Lai

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

Comments 6 pages, 2 figures

2509.11092 2025-09-16 cs.CV cs.AI 57%

PanoLora: Bridging Perspective and Panoramic Video Generation with LoRA Adaptation

Zeyu Dong, Yuyang Yin, Yuqi Li, Eric Li, Hao-Xiang Guo, Yikai Wang

机构 * School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）； Beijing Jiaotong University（北京交通大学）； The City College of New York（纽约城市学院）； Skywork AI

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

2403.12784 2025-09-12 cs.CV 57%

Total Disentanglement of Font Images into Style and Character Class Features

Daichi Haraguchi, Wataru Shimoda, Kota Yamaguchi, Seiichi Uchida

机构 * Kyushu University, Japan（九州大学，日本）； CyberAgent, Japan（CyberAgent，日本）

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

2509.06818 2025-09-09 cs.CV cs.LG 57%

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

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

机构 * UXO Team, Intelligent Creation Lab, ByteDance（字节跳动智能创作实验室）

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

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

2509.04379 2025-09-05 cs.CV cs.AI 57%

SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer

Jimin Xu, Bosheng Qin, Tao Jin, Zhou Zhao, Zhenhui Ye, Jun Yu, Fei Wu

机构 * College of Computer Science and Technology, Zhejiang University（计算机科学与技术学院，浙江大学）

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

2509.01492 2025-09-03 cs.CV 57%

A Continuous-Time Consistency Model for 3D Point Cloud Generation

Sebastian Eilermann, René Heesch, Oliver Niggemann

机构 * Institute for Artificial Intelligence（人工智能研究所）； Helmut Schmidt University（海姆特·施密特大学）

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

2508.21712 2025-09-01 cs.CV 57%

FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA

Alvaro Patricio, Atabak Dehban, Rodrigo Ventura

机构 * Institute for Systems and Robotics, University of Lisbon（系统与机器人研究所，里斯本大学）

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

2508.16696 2025-08-26 cs.GR cs.AI 57%

DecoMind: A Generative AI System for Personalized Interior Design Layouts

Reema Alshehri, Rawan Alotaibi, Leen Almasri, Rawan Altaweel

专题命中个性化与一致性：diffusion(abstract)；分类 cs.GR

Comments ~7 pages; ~32 figures; compiled with pdfLaTeX. Primary category: cs.CV. (Secondary: cs.AI)

2508.14609 2025-08-21 cs.CV 57%

AnchorSync: Global Consistency Optimization for Long Video Editing

Zichi Liu, Yinggui Wang, Tao Wei, Chao Ma

机构 * MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University Shanghai China（人工智能联合实验室，人工智能研究院，上海交通大学）

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

Comments ACM MM 2025; Code is released at https://github.com/VISION-SJTU/AnchorSync

2410.02055 2025-08-19 cs.CV 57%

Style Ambiguity Loss Using CLIP

James Baker

机构 * University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）

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

Comments arXiv admin note: substantial text overlap with arXiv:2407.12009

2508.10937 2025-08-18 cs.CV 57%

Personalized Face Super-Resolution with Identity Decoupling and Fitting

Jiarui Yang, Hang Guo, Wen Huang, Tao Dai, Shutao Xia

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

2412.02287 2025-08-15 cs.CV 57%

Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidance

Qing Zhang, Jinguang Tong, Jing Zhang, Jie Hong, Xuesong Li

机构 * The Australian National University（澳大利亚国立大学）； CSIRO ； The University of Hong Kong（香港大学）

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

2508.09973 2025-08-14 cs.CV 57%

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image

Geonhee Sim, Gyeongsik Moon

机构 * Dept. of CSE, Korea University（计算机科学与工程系，韩国大学）

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

Comments Accepted to ICCV 2025. https://mks0601.github.io/PERSONA/

2508.09461 2025-08-14 cs.CV cs.AI 57%

Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy

Hao Yu, Rupayan Mallick, Margrit Betke, Sarah Adel Bargal

机构 * Boston University（波士顿大学）； Georgetown University（乔治城大学）

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

2508.03034 2025-08-14 cs.CV 57%

MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention

Qi Xie, Yongjia Ma, Donglin Di, Xuehao Gao, Xun Yang

机构 * University of Science and Technology of China（中国科学技术大学）； Li Auto（利汽车）； Northwestern Polytechnical University（西北工业大学）

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

2508.09045 2025-08-13 cs.CV 57%

Per-Query Visual Concept Learning

Ori Malca, Dvir Samuel, Gal Chechik

机构 * Bar‑Ilan University（巴伊兰大学）； OriginAI ； NVIDIA

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

Comments Project page is at https://per-query-visual-concept-learning.github.io/

2508.08248 2025-08-12 cs.CV 57%

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

Shuyuan Tu, Yueming Pan, Yinming Huang, Xintong Han, Zhen Xing, Qi Dai, Chong Luo, Zuxuan Wu, Yu-Gang Jiang

机构 * Fudan University（复旦大学）； Microsoft Research Asia（微软亚洲研究院）； Xi’an Jiaotong University（西安交通大学）； Hunyuan, Tencent Inc.（腾讯 Hunyuan 实验室）

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

2508.07298 2025-08-12 cs.CV 57%

SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations

Zhiqiang Shen, Peng Cao, Xiaoli Liu, Jinzhu Yang, Osmar R. Zaiane

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

2504.18087 2025-08-07 cs.CV 57%

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation

Weipeng Tan, Chuming Lin, Chengming Xu, FeiFan Xu, Xiaobin Hu, Xiaozhong Ji, Junwei Zhu, Chengjie Wang, Yanwei Fu

机构 * Fudan University（复旦大学）； Tencent, YouTu Lab（腾讯、YouTu实验室）

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

Comments Accepted by ACM MM'25. arXiv admin note: text overlap with arXiv:2409.03270

2508.03402 2025-08-06 cs.CV cs.AI cs.LG 57%

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models

Pingchuan Ma, Xiaopei Yang, Yusong Li, Ming Gui, Felix Krause, Johannes Schusterbauer, Björn Ommer

机构 * Munich Center for Machine Learning (MCML)（慕尼黑機器學習中心）

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

Comments ICCV 2025, Project Page: https://compvis.github.io/SCFlow/

1. 个性化与一致性 1272 篇

Unpacking Musical Symbolism in Online Communities: Content-Based and Network-Centric Approaches

PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation

Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation

Personalized Vision via Visual In-Context Learning

ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation

Disentangling Score Content and Performance Style for Joint Piano Rendering and Transcription

T2Bs: Text-to-Character Blendshapes via Video Generation

Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

Generating Detailed Character Motion from Blocking Poses

Lynx: Towards High-Fidelity Personalized Video Generation

Data-driven Smile Design: Personalized Dental Aesthetics Outcomes Using Deep Learning

PanoLora: Bridging Perspective and Panoramic Video Generation with LoRA Adaptation

Total Disentanglement of Font Images into Style and Character Class Features

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward

SSGaussian: Semantic-Aware and Structure-Preserving 3D Style Transfer

A Continuous-Time Consistency Model for 3D Point Cloud Generation

FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA

DecoMind: A Generative AI System for Personalized Interior Design Layouts

AnchorSync: Global Consistency Optimization for Long Video Editing

Style Ambiguity Loss Using CLIP

Personalized Face Super-Resolution with Identity Decoupling and Fitting

Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidance

PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image

Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy

MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention

Per-Query Visual Concept Learning

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation

SynMatch: Rethinking Consistency in Medical Image Segmentation with Sparse Annotations

Disentangle Identity, Cooperate Emotion: Correlation-Aware Emotional Talking Portrait Generation

SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models