图像生成 - arXivDaily 专题

2510.11346 2025-10-14 cs.CV cs.AI 79%

Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation

Joshua Niemeijer, Jan Ehrhardt, Heinz Handels, Hristina Uzunova

机构 * German Aerospace Center (DLR)（德国航空航天中心）； University of Lübeck（吕贝克大学）； German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）

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

Comments Accepted for presentation at ICCV Workshops 2025, "The 4th Workshop on What is Next in Multimodal Foundation Models?" (MMFM)

2510.11650 2025-10-14 cs.CV 70%

InfiniHuman: Infinite 3D Human Creation with Precise Control

Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll

机构 * University of Tübingen, Tübingen AI Center（图宾根大学，图宾根人工智能中心）； University of Tübingen, Tübingen AI Center, MPI for Informatics, SIC（图宾根大学，图宾根人工智能中心，马克斯·普朗克信息研究所，SIC）； University of Tübingen（图宾根大学）

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

Comments Accepted to ACM SIGGRAPH Asia 2025. Project website: https://yuxuan-xue.com/infini-human

2501.19066 2025-10-14 cs.CV 70%

Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations

Dahye Kim, Deepti Ghadiyaram

机构 * Boston University（波士顿大学）； Runway

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

Comments 23 pages, 18 figures

2510.09657 2025-10-14 cs.LG cs.AI cs.NA eess.SP math.NA 67%

Generative Models for Helmholtz Equation Solutions: A Dataset of Acoustic Materials

Riccardo Fosco Gramaccioni, Christian Marinoni, Fabrizio Frezza, Aurelio Uncini, Danilo Comminiello

机构 * 1Department of Information Engineering, Electronics ； Telecommunications (DIET),\ University of Rome, Rome. Italy, \ riccardofosco.gramaccioni

专题命中可控生成：image generation(abstract)；diffusion(abstract)

Comments Accepted at EUSIPCO 2025

2510.11649 2025-10-14 cs.CV 57%

PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

Pradyumna Yalandur Muralidhar, Yuxuan Xue, Xianghui Xie, Margaret Kostyrko, Gerard Pons-Moll

机构 * University of Tübingen, Zuse School ELIZA（图宾根大学Zuse学校ELIZA）； University of Tübingen, Tübingen AI Center（图宾根大学图宾根人工智能中心）； University of Tübingen, Tübingen AI Center, MPI for Informatics, SIC（图宾根大学图宾根人工智能中心、马克斯·普朗克信息研究所、SIC）

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

Comments Accepted to ACM SIGGraphAsia 2025. Project website: https://yuxuan-xue.com/physic

2510.10650 2025-10-14 cs.CV cs.AI 57%

DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis

Peiyin Chen, Zhuowei Yang, Hui Feng, Sheng Jiang, Rui Yan

机构 * College of Artificial Intelligence and Automation, Hohai University（人工智能与自动化学院，河海大学）； College of DaYu, Hohai University（大禹学院，河海大学）； College of Water Conserwancy and Hydropower Engineering, Hohai University（水利水电工程学院，河海大学）； College of Computer Science and Technology, Zhejiang University of Technology（计算机科学与技术学院，浙江工业大学）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments 5 pages

2510.09817 2025-10-14 cs.RO cs.CV 57%

Cross-Sensor Touch Generation

Samanta Rodriguez, Yiming Dou, Miquel Oller, Andrew Owens, Nima Fazeli

机构 * University of Michigan（密歇根大学）； Cornell University（康奈尔大学）

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

Comments CoRL 2025

2510.08561 2025-10-14 cs.CV 57%

MultiCOIN: Multi-Modal COntrollable Video INbetweening

Maham Tanveer, Yang Zhou, Simon Niklaus, Ali Mahdavi Amiri, Hao Zhang, Krishna Kumar Singh, Nanxuan Zhao

机构 * Simon Fraser University（西蒙弗雷泽大学）； Adobe Research（Adobe研究院）

专题命中可控生成：diffusion(abstract)；分类 cs.CV

Comments Project website: https://multicoinx.github.io/multicoin/

1. 可控生成 8 篇

Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation

InfiniHuman: Infinite 3D Human Creation with Precise Control

Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations

Generative Models for Helmholtz Equation Solutions: A Dataset of Acoustic Materials

PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis

Cross-Sensor Touch Generation

MultiCOIN: Multi-Modal COntrollable Video INbetweening