图像生成 - arXivDaily 专题

2509.26231 2025-10-01 cs.CV 79%

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

Jiayi Guo, Chuanhao Yan, Xingqian Xu, Yulin Wang, Kai Wang, Gao Huang, Humphrey Shi

机构 * Tsinghua University（清华大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments ICCV 2025

2509.26025 2025-10-01 cs.CV 79%

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution

Shian Du, Menghan Xia, Chang Liu, Xintao Wang, Jing Wang, Pengfei Wan, Di Zhang, Xiangyang Ji

机构 * Tsinghua University（清华大学）； Kling Team, Kuaishou Technology（快手科技 Kling 团队）； Beijing Institute of Technology（北京理工大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments CVPR 2025

2509.25739 2025-10-01 cs.CV 79%

LieHMR: Autoregressive Human Mesh Recovery with $SO(3)$ Diffusion

Donghwan Kim, Tae-Kyun Kim

机构 * School of Computing, KAIST（计算机学院，韩国科学技术院）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments 17 pages, 13 figures

2509.25681 2025-10-01 cs.RO cs.CV 79%

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought

Junjie Wen, Minjie Zhu, Jiaming Liu, Zhiyuan Liu, Yicun Yang, Linfeng Zhang, Shanghang Zhang, Yichen Zhu, Yi Xu

机构 * Midea Group（美的集团）； Peking University（北京大学）； Shanghai Jiaotong University（上海交通大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments technique report

2509.25304 2025-10-01 cs.CV 79%

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model

Haozhe Jia, Wenshuo Chen, Yuqi Lin, Yang Yang, Lei Wang, Mang Ning, Bowen Tian, Songning Lai, Nanqian Jia, Yifan Chen, Yutao Yue

机构 * HKUST-GZ（香港科技大学-广州校区）； Shandong University（山东大学）； UESTC（电子科技大学）； Griffith University（格里菲斯大学）； Data61/CSIRO ； Utrecht University（乌得勒支大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； Peking University（北京大学）； Institute of Deep Perception Technology, JITRI（JITRI深度感知技术研究院）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.25280 2025-10-01 eess.IV cs.CV 79%

Anatomy-DT: A Cross-Diffusion Digital Twin for Anatomical Evolution

Moinak Bhattacharya, Gagandeep Singh, Prateek Prasanna

机构 * Stony Brook University（斯通布罗克大学）； Columbia University（哥伦比亚大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2507.13343 2025-10-01 cs.CV eess.IV 79%

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds

Yushu Wu, Yanyu Li, Anil Kag, Ivan Skorokhodov, Willi Menapace, Ke Ma, Arpit Sahni, Ju Hu, Aliaksandr Siarohin, Dhritiman Sagar, Yanzhi Wang, Sergey Tulyakov

机构 * Snap Inc.（Snap公司）； Northeastern University（东北大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments 21 pages, 9 figures, 13 tables

2507.03054 2025-10-01 cs.CV cs.AI 79%

LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection

Ana Vasilcoiu, Ivona Najdenkoska, Zeno Geradts, Marcel Worring

机构 * University of Amsterdam（阿姆斯特丹大学）； Netherlands Forensic Institute (NFI)（荷兰法医学研究所）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2503.08643 2025-10-01 stat.ML cs.AI cs.CV cs.LG 79%

Rethinking Diffusion Model in High Dimension

Zhenxin Zheng, Zhenjie Zheng

机构 * MTLab, Meitu Inc.（美图公司MT实验室）； Civil Engineering, University of Hong Kong（香港大学土木工程系）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.24997 2025-09-30 cs.CV 79%

PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion

Yuyang Yin, HaoXiang Guo, Fangfu Liu, Mengyu Wang, Hanwen Liang, Eric Li, Yikai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei

机构 * Beijing Jiaotong University（北京交通大学）； Skywork AI ； Tsinghua University（清华大学）； University of Toronto（多伦多大学）； Beijing Normal University（北京师范大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments Project page: \url{https://yuyangyin.github.io/PanoWorld-X/}

2509.24903 2025-09-30 cs.RO cs.CV eess.IV 79%

DRCP: Diffusion on Reinforced Cooperative Perception for Perceiving Beyond Limits

Lantao Li, Kang Yang, Rui Song, Chen Sun

机构 * Sony (China) Limited（索尼（中国）有限公司）； Renmin University of China（中国人民大学）； Fraunhofer IVI（弗劳恩霍夫IVI研究所）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.24580 2025-09-30 cs.LG cs.CV 79%

SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse Problems

Lingyu Wang, Xiangming Meng

机构 * Zhejiang University（浙江大学）； ZJU-UIUC Institute（浙大UIUC研究院）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.24227 2025-09-30 eess.IV cs.CV cs.LG 79%

Non-Invasive Detection of PROState Cancer with Novel Time-Dependent Diffusion MRI and AI-Enhanced Quantitative Radiological Interpretation: PROS-TD-AI

Baltasar Ramos, Cristian Garrido, Paulette Narv'aez, Santiago Gelerstein Claro, Haotian Li, Rafael Salvador, Constanza V'asquez-Venegas, Iv'an Gallegos, Yi Zhang, V'ictor Casta~neda, Cristian Acevedo, Dan Wu, Gonzalo C'ardenas, Camilo G. Sotomayor

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments Study protocol preprint (not peer reviewed). Prepared with the MDPI Journal of Imaging Word author template. Primary category: eess.IV. Code and patient data are not publicly available due to privacy; requests will be considered under a data-use agreement

2509.24194 2025-09-30 cs.CV 79%

An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

Zach Eidex, Mojtaba Safari, Jie Ding, Richard Qiu, Justin Roper, David Yu, Hui-Kuo Shu, Zhen Tian, Hui Mao, Xiaofeng Yang

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.24185 2025-09-30 cs.CV 79%

Simulating Post-Neoadjuvant Chemotherapy Breast Cancer MRI via Diffusion Model with Prompt Tuning

Jonghun Kim, Hyunjin Park

机构 * Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Korea（电子与计算机工程系，成均馆大学，Suwon, Korea）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments ISBI'25, 5 pages, 4 figures

2509.23971 2025-09-30 cs.CV 79%

VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic Diffusion

Kargi Chauhan, Leilani H. Gilpin

机构 * University of California, Santa Cruz（加州大学圣克鲁兹分校）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.21839 2025-09-30 cs.CV cs.AI 79%

DiTraj: training-free trajectory control for video diffusion transformer

Cheng Lei, Jiayu Zhang, Yue Ma, Xinyu Wang, Long Chen, Liang Tang, Yiqiang Yan, Fei Su, Zhicheng Zhao

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； Lenovo（联想）； HKUST（香港科技大学）； Tsinghua University（清华大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2507.09212 2025-09-30 cs.LG cs.CV stat.ML 79%

Warm Starts Accelerate Conditional Diffusion

Jonas Scholz, Richard E. Turner

机构 * University of Cambridge（剑桥大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments 10 pages, 6 figures

2505.17550 2025-09-30 cs.CV 79%

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models

Xiaoyu Ye, Songjie Cheng, Yongtao Wang, Yajiao Xiong, Yishen Li

机构 * Peking University（北京大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2503.10549 2025-09-30 cs.CV cs.CR 79%

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion

Youngjin Kwon, Xiao Zhang

机构 * CISPA Helmholtz Center for Information Security（CISPA信息安全研究中心）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.23906 2025-09-30 cs.CV cs.AI 79%

EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical Imaging

Anoushka Harit, William Prew, Zhongtian Sun, Florian Markowetz

机构 * University of Cambridge（剑桥大学）； University of Kent（肯特大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments Accepted at AI That Keeps Up: NeurIPS 2025 Workshop on Continual and Compatible Foundation Model Updates

2509.23723 2025-09-30 cs.CV 79%

DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion

Zijun Li, Hongyu Yan, Shijie Li, Kunming Luo, Li Lu, Xulei Yang, Weisi Lin

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.23625 2025-09-30 cs.CV cs.AI cs.CL cs.LG 79%

RIV: Recursive Introspection Mask Diffusion Vision Language Model

YuQian Li, Limeng Qiao, Lin Ma

机构 * Meituan（美团）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.23603 2025-09-30 cs.CV 79%

MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising

Tangtangfang Fang, Jingxi Hu, Xiangjian He, Jiaqi Yang

机构 * School of Computer Science, University of Nottingham Ningbo China（诺丁汉大学宁波校区计算机科学学院）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments Submitted to ICASSP 2026

2509.22723 2025-09-30 cs.CR cs.CV 79%

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models

Kang Wei, Xin Yuan, Fushuo Huo, Chuan Ma, Long Yuan, Songze Li, Ming Ding, Dacheng Tao

机构 * School of Cyber Science and Engineering, Southeast University（电子科技大学信息与通信工程学院）； Data61, CSIRO（数据61，CSIRO）； Zhejiang Laboratory（浙江省实验室）； school of Computer Science and Artificial Intelligence, Wuhan University of Technology（计算机科学与人工智能学院，武汉理工大学）； College of Computing and Data Science, Nanyang Technological University（计算科学与数据科学学院，南洋理工大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2509.05992 2025-09-30 cs.CV 79%

Physics-Guided Null-Space Diffusion with Sparse Masking for Corrective Sparse-View CT Reconstruction

Zekun Zhou, Yanru Gong, Liu Shi, Qiegen Liu

机构 * School of Information Engineering, Nanchang University, Nanchang, China（信息工程学院，南昌大学，南昌，中国）； School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China（数学与计算机科学学院，南昌大学，南昌，中国）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2506.23801 2025-09-30 cs.CV 79%

Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolution

Ce Wang, Wanjie Sun

机构 * School of Remote Sensing and Information Engineering, Wuhan University（遥感与信息工程学院，武汉大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2505.21325 2025-09-30 cs.CV 79%

MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on

Guangyuan Li, Siming Zheng, Hao Zhang, Jinwei Chen, Junsheng Luan, Binkai Ou, Lei Zhao, Bo Li, Peng-Tao Jiang

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

2503.23402 2025-09-30 cs.CV cs.AI 79%

Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge

Junsu Kim, Yunhoe Ku, Dongyoon Han, Seungryul Baek

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

Comments pre-print ver 2

2502.00639 2025-09-30 cs.CV cs.AI cs.LG stat.ML 79%

Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer

Tao Ren, Zishi Zhang, Jingyang Jiang, Zehao Li, Shentao Qin, Yi Zheng, Guanghao Li, Qianyou Sun, Yan Li, Jiafeng Liang, Xinping Li, Yijie Peng

机构 * Peking University（北京大学）

专题命中扩散模型：diffusion(title,abstract)；分类 cs.CV

1. 扩散模型 70196 篇

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution

LieHMR: Autoregressive Human Mesh Recovery with $SO(3)$ Diffusion

dVLA: Diffusion Vision-Language-Action Model with Multimodal Chain-of-Thought

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model

Anatomy-DT: A Cross-Diffusion Digital Twin for Anatomical Evolution

Taming Diffusion Transformer for Efficient Mobile Video Generation in Seconds

LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection

Rethinking Diffusion Model in High Dimension

PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion

DRCP: Diffusion on Reinforced Cooperative Perception for Perceiving Beyond Limits

SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse Problems

Non-Invasive Detection of PROState Cancer with Novel Time-Dependent Diffusion MRI and AI-Enhanced Quantitative Radiological Interpretation: PROS-TD-AI

An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

Simulating Post-Neoadjuvant Chemotherapy Breast Cancer MRI via Diffusion Model with Prompt Tuning

VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic Diffusion

DiTraj: training-free trajectory control for video diffusion transformer

Warm Starts Accelerate Conditional Diffusion

T2VUnlearning: A Concept Erasing Method for Text-to-Video Diffusion Models

Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion

EWC-Guided Diffusion Replay for Exemplar-Free Continual Learning in Medical Imaging

DiffPCN: Latent Diffusion Model Based on Multi-view Depth Images for Point Cloud Completion

RIV: Recursive Introspection Mask Diffusion Vision Language Model

MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models

Physics-Guided Null-Space Diffusion with Sparse Masking for Corrective Sparse-View CT Reconstruction

Controllable Reference Guided Diffusion with Local Global Fusion for Real World Remote Sensing Image Super Resolution

MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on

Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge

Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer