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。

2025-11-11 至 2025-11-11 共收录 125 信号源:cs.CV, cs.GR, cs.MM

1. 扩散模型 89 篇

2511.06079 2025-11-11 math.PR math.OC 50%

The Schrödinger Bridge Problem for Jump Diffusions with Regime Switching

Andrei Zlotchevski, Linan Chen

专题命中 扩散模型 :diffusion(abstract)

Comments 44 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05776 2025-11-11 math.NA cs.NA 50%

A Spectral LOD Method for Multiscale Problems with High Contrast

Susanne C. Brenner, José C. Garay, Li-yeng Sung

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05629 2025-11-11 cs.LG cs.AI physics.ao-ph 50%

SSTODE: Ocean-Atmosphere Physics-Informed Neural ODEs for Sea Surface Temperature Prediction

Zheng Jiang, Wei Wang, Gaowei Zhang, Yi Wang

专题命中 扩散模型 :diffusion(abstract)

Comments To be published in the Proceedings of AAAI-AISI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05535 2025-11-11 cs.CL cs.DB cs.IT math.IT 50%

Future of AI Models: A Computational perspective on Model collapse

Trivikram Satharasi, S Sitharama Iyengar

机构 * University of Florida(佛罗里达大学) Florida International University(佛罗里达国际大学)

专题命中 扩散模型 :diffusion(abstract)

Comments Submitted to Springer Nature. Code Available at https://github.com/t-satharasi/AI-Modal-Collapse-Code-for-Reproduction.git

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.01853 2025-11-11 cond-mat.str-el cond-mat.mtrl-sci 50%

Quantum Acoustics Demystifies the Strange Metals

Eric J. Heller, Alhun Aydin, Anton M. Graf, Joost de Nijs, Yoel Zimmermann, Xiaoyu Ouyang, Shaobing Yuan, Zixuan Chai, Siyuan Chen, Jasper Jain, Mingxuan Xiao, Chenzheng Yu, Zhongling Lu, Joonas Keski-Rahkonen

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11593 2025-11-11 cond-mat.supr-con cond-mat.mtrl-sci 50%

Low barrier ZrO$_x$-based Josephson junctions

Jaehong Choi, Maciej Olszewski, Luojia Zhang, Zhaslan Baraissov, Tathagata Banerjee, Kushagra Aggarwal, Sarvesh Chaudhari, Tomás A. Arias, David A. Muller, Valla Fatemi, Gregory D. Fuchs

专题命中 扩散模型 :diffusion(abstract)

Comments 32 pages in manuscript format

Journal ref APL Mater. 13, 111103 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03624 2025-11-11 astro-ph.EP astro-ph.SR 50%

Radiative Nonideal MHD Simulations of Inner Protoplanetary Disks: Temperature Structures, Asymmetric Winds, and Episodic Surface Accretion

Shoji Mori, Xue-Ning Bai, Kengo Tomida

专题命中 扩散模型 :diffusion(abstract)

Comments Accepted for publication in ApJ; 31 pages, 21 figures; Comments are welcome

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00357 2025-11-11 cs.LG 50%

Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization

Yoonhyuk Choi, Jiho Choi, Chong-Kwon Kim

专题命中 扩散模型 :diffusion(abstract)

Comments AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07096 2025-11-11 cs.RO cs.AI cs.LG 50%

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real

Prithwish Dan, Kushal Kedia, Angela Chao, Edward Weiyi Duan, Maximus Adrian Pace, Wei-Chiu Ma, Sanjiban Choudhury

机构 * Cornell University(康奈尔大学)

专题命中 扩散模型 :diffusion(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.11718 2025-11-11 math.PR math.CO 50%

A Probabilistic Parking Process and Labeled IDLA

Pamela E. Harris, Thiago Holleben, J. Carlos Martínez Mori, Amanda Priestley, Keith Sullivan, Per Wagenius

专题命中 扩散模型 :diffusion(abstract)

Comments 32 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏

2. 可控生成 12 篇

2505.11468 2025-11-11 cs.CV 85%

PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment

Dingbang Huang, Wenbo Li, Yifei Zhao, Xinyu Pan, Chun Wang, Yanhong Zeng, Bo Dai

机构 * Shanghai Jiao Tong University(上海交通大学) The Chinese University of Hong Kong(香港中文大学) Zhejiang University(浙江大学) Shanghai AI Laboratory(上海人工智能实验室) The University of Hong Kong(香港大学)

专题命中 可控生成 :image generation(title,abstract);text-to-image(abstract);diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.00596 2025-11-11 cs.CV 83%

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

Danfeng Li, Hui Zhang, Sheng Wang, Jiacheng Li, Zuxuan Wu

机构 * Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University(上海智能信息处理关键实验室,复旦大学计算机学院) Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心) HiThink Research(HiThink研究机构)

专题命中 可控生成 :image generation(title);text-to-image(abstract);diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07091 2025-11-11 cs.CV cs.AI 79%

How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions

Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen

专题命中 可控生成 :text-to-image(title,abstract);分类 cs.CV

Comments Accepted for publication at the Alignment Track of The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10684 2025-11-11 cs.LG math.OC stat.CO stat.ML 71%

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Yuchen Zhu, Wei Guo, Jaemoo Choi, Guan-Horng Liu, Yongxin Chen, Molei Tao

机构 * Georgia Institute of Technology(佐治亚理工学院) FAIR at Meta(Meta的FAIR)

专题命中 可控生成 :diffusion(title)

Comments NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06002 2025-11-11 cs.CV 70%

MALeR: Improving Compositional Fidelity in Layout-Guided Generation

Shivank Saxena, Dhruv Srivastava, Makarand Tapaswi

机构 * Adobe Research(Adobe研究)

专题命中 可控生成 :image generation(abstract);text-to-image(abstract);分类 cs.CV

Comments ACM TOG Dec 2025, Siggraph Asia, Project page: https://katha-ai.github.io/projects/maler/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06709 2025-11-11 cs.CV 57%

K-Stain: Keypoint-Driven Correspondence for H&E-to-IHC Virtual Staining

Sicheng Yang, Zhaohu Xing, Haipeng Zhou, Lei Zhu

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) The Hong Kong University of Science and Technology(香港科技大学)

专题命中 可控生成 :image generation(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.18232 2025-11-11 cs.CV 57%

Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain

Wenshuo Chen, Haozhe Jia, Songning Lai, Lei Wang, Yuqi Lin, Hongru Xiao, Lijie Hu, Yutao Yue

机构 * Shandong University(山东大学) Griffith University(格里菲斯大学) Data61/CSIRO Tongji University(同济大学)

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06271 2025-11-11 cs.CV 57%

RelightMaster: Precise Video Relighting with Multi-plane Light Images

Weikang Bian, Xiaoyu Shi, Zhaoyang Huang, Jianhong Bai, Qinghe Wang, Xintao Wang, Pengfei Wan, Kun Gai, Hongsheng Li

机构 * Multimedia Laboratory, The Chinese University of Hong Kong(香港中文大学多媒体实验室) Kling Team, Kuaishou Technology(快手技术 Kling 团队) CPII under InnoHK(创新香港 CPII) Zhejiang University(浙江大学) Dalian University of Technology(大连理工大学)

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

Comments Project Page: https://wkbian.github.io/Projects/RelightMaster/

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.20358 2025-11-11 cs.CV 57%

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Chen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou, Yuan Liu, Jiatao Gu, Lingjie Liu

机构 * University of Pennsylvania(宾夕法尼亚大学) HKU(香港大学) HKUST(香港科技大学)

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

Comments NeurIPS 2025 Camera Ready Version

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.09649 2025-11-11 cs.AI cs.CV cs.LG cs.RO 57%

ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policy

Yuhang Dong, Haizhou Ge, Yupei Zeng, Jiangning Zhang, Beiwen Tian, Hongrui Zhu, Yufei Jia, Ruixiang Wang, Zhucun Xue, Guyue Zhou, Longhua Ma, Guanzhong Tian

机构 * Ningbo Global Innovation Center, Zhejiang University(浙江大学宁波全球创新中心) Tsinghua University(清华大学) Youtu, Tencent(腾讯优图) The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)) College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院)

专题命中 可控生成 :diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05763 2025-11-11 cond-mat.supr-con 50%

Controllable Superconductivity in Suspended van der Waals Materials

Ruihuan Fang, Cuiju Yu, Youqiang Huang, Tosson Elalaily, Yuvraj Chaudhry, Yaoqiang Zhou, Andres Castellanos-Gomez, Sanshui Xiao, Jiwon Park, Hyunyong Choi, Fida Ali, Hanlin Fang, Jose Lado, Pertti Hakonen, Zhipei Sun

专题命中 可控生成 :diffusion(abstract)

Comments 13 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.23643 2025-11-11 cs.RO 50%

SceneComplete: Open-World 3D Scene Completion in Cluttered Real World Environments for Robot Manipulation

Aditya Agarwal, Gaurav Singh, Bipasha Sen, Tomás Lozano-Pérez, Leslie Pack Kaelbling

机构 * Computer Science and Artificial Intelligence Laboratory, MIT(计算机科学与人工智能实验室,麻省理工学院)

专题命中 可控生成 :inpainting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

3. 图像修复 6 篇

2509.23919 2025-11-11 cs.CV 83%

Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models

Longtao Jiang, Jie Huang, Mingfei Han, Lei Chen, Yongqiang Yu, Feng Zhao, Xiaojun Chang, Zhihui Li

专题命中 图像修复 :inpainting(title,abstract);diffusion(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2202.06358 2025-11-11 cs.CV cs.AI cs.GR cs.MM 82%

Do Inpainting Yourself: Generative Facial Inpainting Guided by Exemplars

Wanglong Lu, Hanli Zhao, Xianta Jiang, Xiaogang Jin, Yongliang Yang, Min Wang, Jiankai Lyu, Kaijie Shi

专题命中 图像修复 :inpainting(title,abstract);分类 cs.CV、cs.GR、cs.MM

Comments There are 16 pages, 18 figures in this paper. Homepage: https://longlongaaago.github.io/EXE-GAN/

Journal ref Neurocomputing 617 (2025): 128996

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06457 2025-11-11 cs.CV 79%

Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes

Shaoxiang Wang, Shihong Zhang, Christen Millerdurai, Rüdiger Westermann, Didier Stricker, Alain Pagani

机构 * German Research Center for Artificial Intelligence(德国人工智能研究中心) RPTU(鲁尔蓬德大学) Technical University of Munich(慕尼黑技术大学)

专题命中 图像修复 :inpainting(title,abstract);分类 cs.CV

Comments WACV 2026, project page: https://dfki-av.github.io/inpaint360gs/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06748 2025-11-11 cs.CV 57%

Image Restoration via Primal Dual Hybrid Gradient and Flow Generative Model

Ji Li, Chao Wang

专题命中 图像修复 :inpainting(abstract);分类 cs.CV

Comments 13 pages; AAAI26 version with appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07116 2025-11-11 cs.SD 50%

BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspective

Andong Li, Tong Lei, Rilin Chen, Kai Li, Meng Yu, Xiaodong Li, Dong Yu, Chengshi Zheng

专题命中 图像修复 :diffusion(abstract)

Comments 18 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06774 2025-11-11 math.OC cs.LG 50%

Bilevel Learning via Inexact Stochastic Gradient Descent

Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt

机构 * EPSRC Centre for Doctoral Training in Statistical Applied Mathematics at Bath(巴斯大学统计应用数学博士培训中心) Australian Research Council(澳大利亚研究理事会) Indian Institute of Technology (IIT), Kharagpur(印度理工学院(Kharagpur分校)) University of Melbourne(墨尔本大学) Department of Electronics & Electrical Communication Engineering(电子与电气通信工程系) School of Mathematics and Statistics(数学与统计学学院)

专题命中 图像修复 :inpainting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏

4. 个性化与一致性 2 篇

2511.06721 2025-11-11 cs.CV 70%

AvatarTex: High-Fidelity Facial Texture Reconstruction from Single-Image Stylized Avatars

Yuda Qiu, Zitong Xiao, Yiwei Zuo, Zisheng Ye, Weikai Chen, Xiaoguang Han

机构 * SSE, CUHKSZ(CUHKSZ 信息学院) FNii, CUHKSZ(CUHKSZ 信息学院)

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

Comments 3DV 2026 Accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07233 2025-11-11 cs.CV cs.LG 57%

Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detection

Alexander Bauer, Klaus-Robert Müller

机构 * Machine Learning Group, TU Berlin(柏林技术大学机器学习组) BIFOLD, Berlin, Germany(柏林BIFOLD) Dept. of AI, Korea University, Seoul, Republic of Korea(韩国大学人工智能系) MPI for Informatics, Saarbrücken, Germany(信息学Max Planck研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏