arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

图像生成

图像生成、文生图、图像编辑、扩散模型和可控生成。

共收录 1266 信号源:cs.CV, cs.GR, cs.MM

1. 个性化与一致性 1266 篇

2209.05968 2022-09-14 cs.CV 74%

Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation

Dae-Young Song, Geonsoo Lee, HeeKyung Lee, Gi-Mun Um, Donghyeon Cho

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

Comments Accepted by ECCV2022 (poster)

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.02311 2022-08-05 cs.CV cs.LG 74%

Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers

Amar Kumar, Anjun Hu, Brennan Nichyporuk, Jean-Pierre R. Falet, Douglas L. Arnold, Sotirios Tsaftaris, Tal Arbel

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

Comments Accepted to the MIABID workshop at MICCAI 2022

详情

展开后加载摘要…

URL PDF HTML 收藏
2205.02439 2022-05-06 cs.CV cs.AI 74%

Text to artistic image generation

Qinghe Tian, Jean-Claude Franchitti

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

Comments 7 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.16146 2021-07-26 cs.CV 74%

Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation

Gihyun Kwon, Jong Chul Ye

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

Comments ICCV 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.12288 2020-04-28 cs.CV 74%

Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation

Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki

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

Comments Accepted for main conference in EMBC 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
1901.04686 2019-01-16 cs.GR 74%

Image Synthesis and Style Transfer

Somnuk Phon-Amnuaisuk

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

Comments 11 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
1808.03944 2018-08-14 cs.CV cs.AI cs.LG eess.IV 74%

Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks

Chengjia Wang, Gillian Macnaught, Giorgos Papanastasiou, Tom MacGillivray, David Newby

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1611.02200 2016-11-08 cs.CV 74%

Unsupervised Cross-Domain Image Generation

Yaniv Taigman, Adam Polyak, Lior Wolf

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.07543 2026-03-10 cs.CV cs.MM 73%

CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

CONSTANT:通过补丁对比增强和风格感知量化实现高质量单次手写生成

Anh-Duy Le, Van-Linh Pham, Thanh-Nam Vo, Xuan Toan Mai, Tuan-Anh Tran

机构 * Viettel Artificial Intelligence and Data Services Center(越南 Viettel 人工智能与数据服务中心) Ho Chi Minh City University of Technology(胡志明市技术大学)

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

AI总结 CONSTANT通过补丁对比增强和风格感知量化,实现高质量单次手写生成,有效提升图像细节与风格适应性。

Comments Accepted as oral presentation at WACV 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06038 2026-03-09 cs.CV cs.GR 73%

FontUse: A Data-Centric Approach to Style- and Use-Case-Conditioned In-Image Typography

FontUse: 一种以数据为中心的方法用于风格和使用场景条件下的图像内字体设计

Xia Xin, Yuki Endo, Yoshihiro Kanamori

机构 * University of Tsukuba(茨口大学)

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

AI总结 FontUse提出了一种以数据为中心的方法,通过构建大规模字体数据集并结合多模态模型,提升文本生成中字体风格和使用场景的控制能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.19056 2025-04-29 cs.CV cs.AI cs.CL cs.LG cs.MM 73%

Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions

Mohammad Mahdi Abootorabi, Omid Ghahroodi, Pardis Sadat Zahraei, Hossein Behzadasl, Alireza Mirrokni, Mobina Salimipanah, Arash Rasouli, Bahar Behzadipour, Sara Azarnoush, Benyamin Maleki, Erfan Sadraiye, Kiarash Kiani Feriz, Mahdi Teymouri Nahad, Ali Moghadasi, Abolfazl Eshagh Abianeh, Nizi Nazar, Hamid R. Rabiee, Mahdieh Soleymani Baghshah, Meisam Ahmadi, Ehsaneddin Asgari

机构 * Computer Engineering Department, Sharif University of Technology(谢里夫理工大学计算机工程系) Iran University of Science and Technology(伊朗科学技术大学) Qatar Computing Research Institute(卡塔尔计算研究院)

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

Comments 50 main pages, 30 pages appendix, 21 figures, 8 tables, GitHub Repository: https://github.com/llm-lab-org/Generative-AI-for-Character-Animation-Survey

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.14844 2025-02-21 cs.GR cs.CV cs.LG 73%

Dynamic Concepts Personalization from Single Videos

Rameen Abdal, Or Patashnik, Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Sergey Tulyakov, Daniel Cohen-Or, Kfir Aberman

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

Comments Webpage: https://snap-research.github.io/dynamic_concepts/

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.11202 2024-06-18 cs.CV cs.GR 73%

Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models

Tianfu Wang, Anton Obukhov, Konrad Schindler

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.05800 2024-05-10 cs.GR cs.CV 73%

DragGaussian: Enabling Drag-style Manipulation on 3D Gaussian Representation

Sitian Shen, Jing Xu, Yuheng Yuan, Xingyi Yang, Qiuhong Shen, Xinchao Wang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19358 2026-08-06 cs.CL cs.AI 71%

Benchmarking and Improving LLM Robustness for Personalized Generation

Chimaobi Okite, Naihao Deng, Kiran Bodipati, Huaidian Hou, Joyce Chai, Rada Mihalcea

机构 * University of Michigan(密歇根大学)

专题命中 个性化与一致性 :personalized generation(title)

Comments First draft. First camera-ready version

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10293 2026-07-16 math.NA cs.NA 版本更新 71%

An improved estimate of the intermediate internal energy in the energy-consistent HLLD scheme

关于《HLL型MHD黎曼求解器中间状态的能量一致性》中HLLD型格式的数值扩散问题

Fan Zhang

专题命中 个性化与一致性 :diffusion(title)

AI总结 研究针对戴 - 伍德沃德激波管问题中HLLD-ec格式出现的密度振荡,提出对该格式的简单修改,核心方法是修改格式,主要贡献是消除了密度振荡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.00742 2026-06-02 cs.CL 71%

CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs

CURP: 基于码本的连续用户表示用于大语言模型的个性化生成

Liang Wang, Xinyi Mou, Xiaoyou Liu, Xuanjing Huang, Zhongyu Wei

机构 * School of Data Science, Fudan University(复旦大学数据科学学院) Shanghai Innovation Institute(上海创新研究院) School of Computer Science, Fudan University(复旦大学计算机科学学院)

专题命中 个性化与一致性 :personalized generation(title)

AI总结 提出CURP框架,通过双向用户编码器和离散原型码本提取多维用户特征,实现少量可训练参数的即插即用个性化生成,在变体生成任务上优于强基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02713 2025-12-03 cs.AI 71%

Training Data Attribution for Image Generation using Ontology-Aligned Knowledge Graphs

利用本体对齐的知识图谱训练数据归因于图像生成

Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis, Joemon M. Jose

机构 * National Centre for Scientific Research ``Demokritos''(国家科学研究中心「德莫克里特」) University of Glasgow(格拉斯哥大学)

专题命中 个性化与一致性 :image generation(title)

AI总结 本文提出利用本体对齐的知识图谱方法,通过多模态大语言模型提取图像中的结构化三元组,以追踪生成模型中训练数据的影响,从而提升透明度和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.07088 2025-08-18 cs.CL 71%

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference

Yanming Liu, Xinyue Peng, Ningjing Sang, Yafeng Yan, Xiaolan Ke, Zhiting Zheng, Shaobo Liu, Songhang Deng, Jiannan Cao, Le Dai, Xingzu Liu, Ruilin Nong, Weihao Liu

机构 * Zhejiang University(浙江大学) Southeast University(东南大学) The Fu Foundation School of Engineering and Applied Science, Columbia University(哥伦比亚大学工程与应用科学学院) Stevens Institute of Technology(斯蒂文斯理工学院) Harvard University(哈佛大学) MIT(麻省理工学院) UCLA(加州大学洛杉矶分校) Beijing Institute of Technology(北京理工大学) Tianjin University(天津大学)

专题命中 个性化与一致性 :personalized generation(title)

Comments Update for details

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17571 2025-05-26 cs.CL 71%

Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation

Sichun Luo, Guanzhi Deng, Jian Xu, Xiaojie Zhang, Hanxu Hou, Linqi Song

机构 * Dongguan University of Technology(东莞理工大学) City University of Hong Kong(香港城市大学) Tsinghua University(清华大学) Guangzhou University(广州大学)

专题命中 个性化与一致性 :personalized generation(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2304.09225 2023-04-20 q-bio.QM 71%

Modulating human brain responses via optimal natural image selection and synthetic image generation

Zijin Gu, Keith Jamison, Mert R. Sabuncu, Amy Kuceyeski

专题命中 个性化与一致性 :image generation(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
2204.12902 2022-04-28 cs.SI 71%

A Graph Diffusion Scheme for Decentralized Content Search based on Personalized PageRank

Nikolaos Giatsoglou, Emmanouil Krasanakis, Symeon Papadopoulos, Ioannis Kompatsiaris

专题命中 个性化与一致性 :diffusion(title)

Comments 7 pages, 3 figures, to be published in the Decentralized Internet, Networks, Protocols, and Systems (DINPS 2022) workshop hosted at the 42nd IEEE International Conference on Distributed Computing Systems (ICDCS 2022) - https://research.protocol.ai/sites/dinps/

详情

展开后加载摘要…

URL PDF HTML 收藏
2003.11958 2020-06-12 cs.LG stat.ML 71%

StrokeCoder: Path-Based Image Generation from Single Examples using Transformers

Sabine Wieluch, Friedhelm Schwenker

专题命中 个性化与一致性 :image generation(title)

详情

展开后加载摘要…

URL PDF HTML 收藏
1512.05485 2016-02-17 physics.soc-ph cs.SI 71%

Improving personalized link prediction by hybrid diffusion

Jin-Hu Liu, Yu-Xiao Zhu, Tao Zhou

专题命中 个性化与一致性 :diffusion(title)

Journal ref Physica A 447 (2016) 199-207

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.04448 2026-08-06 cs.CV cs.AI 新提交 70%

When does training on downscaled images yield the same gradients?

在降采样图像上进行训练何时能产生相同的梯度?

Seunghyun Ji

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

AI总结 该研究探究降采样图像训练的梯度一致性,推导梯度变化的两个项,发现特定噪声窗口内降采样梯度与原生梯度接近,据此训练LoRA适配器可减少14.6%训练时间且性能接近原生。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03822 2026-08-05 cs.CV cs.AI 新提交 70%

FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis

FlowForm:融合流体物理与拓扑一致性的卫星洪水合成方法

Zhang Weihui, Wang Ruizhi, Xu Hongye, Wang Huiqiong, Sun Li, Song Mingli

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

AI总结 FlowForm是融合流体物理与拓扑一致性的卫星洪水合成框架,通过FDM、TAA及FloodScape数据集,在洪水图像生成的视觉保真度、配对图像相似性等指标上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03708 2026-08-05 cs.CV 新提交 70%

MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding

MultiCompose:基于每个主体属性绑定的多概念个性化生成

Ruirui Zhang, Zhengkai Zhao, Pan Gao

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

AI总结 MultiCompose是解耦多概念个性化与多主体推理的图像生成框架,通过语义保留正则化和两阶段推理解决主体身份退化与属性错位问题,引入的MSP-Bench可联合评估相关指标,性能优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01973 2026-08-05 cs.CV 版本更新 70%

NearID: Identity Representation Learning via Near-identity Distractors

NearID: 通过近身份干扰实现身份表示学习

Aleksandar Cvejic, Rameen Abdal, Abdelrahman Eldesokey, Bernard Ghanem, Peter Wonka

机构 * King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学) Snap Research(Snap研究院)

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

AI总结 本文提出NearID框架,通过近身份干扰消除背景影响,提升身份识别精度,改进模型在个性化生成和图像编辑任务中的表现。

Comments Accepted to ECCV 2026, Code, model, and dataset are released, visit https://github.com/Gorluxor/NearID

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00674 2026-08-04 cs.CV 新提交 70%

CopyCat: Improving Fine-Grained Subject Consistency in Subject-to-Image Models within Seconds

CopyCat:在数秒内提升主体到图像模型中的细粒度主体一致性

Peng Zheng, Ruiqi Liu, Rui Ma, Zuxuan Wu

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

AI总结 本研究提出轻量级模型精调框架CopyCat,通过附加FCLoRA在数秒内提升主体到图像模型的细粒度主体一致性,经DreamBench等实验验证,可适配多样未见过的主体与提示并取得持续效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.25962 2026-07-29 cs.CV 新提交 70%

LaP-Forensics: Latent-Pixel Consistency Guided Multimodal Reasoning for Deepfake Detection

LaP-Forensics:用于深度伪造检测的潜在像素一致性引导的多模态推理

Can Wang, Yuhao Wang, Yushe Cao, Canran Xiao, Fei Shen

机构 * The Hong Kong Polytechnic University(香港理工大学) University College London(伦敦大学学院) Tsinghua University(清华大学) Sun Yat-sen University(中山大学) National University of Singapore(新加坡国立大学)

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

AI总结 研究针对深度伪造检测问题,提出LaP-Forensics多模态框架,利用基于重建的取证证据及结构化模型预测,经组相对策略优化,实现跨生成器检测和伪影定位,实验验证了残差流效用,但后处理下文本忠实性和可靠性有局限。

Comments Accepted at ACM Multimedia 2026 (ACM MM 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏