图像生成 - arXivDaily 专题

2509.17024 2025-09-23 cs.CV cs.AI 79%

When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration

Wenxuan Fang, Jili Fan, Chao Wang, Xiantao Hu, Jiangwei Weng, Ying Tai, Jian Yang, Jun Li

机构 * School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）； School of Electrical Engineering, Southeast University（电气工程学院，东南大学）； School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学）

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

2509.16897 2025-09-23 cs.CV 79%

PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion

Xuewan He, Jielei Wang, Zihan Cheng, Yuchen Su, Shiyue Huang, Guoming Lu

机构 * University of Electronic Science and Technology of China（电子科技大学）

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

2507.13797 2025-09-23 cs.CV 79%

DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance

Huu-Phu Do, Yu-Wei Chen, Yi-Cheng Liao, Chi-Wei Hsiao, Han-Yang Wang, Wei-Chen Chiu, Ching-Chun Huang

机构 * National Yang Ming Chiao Tung University（国家阳明交通大学）； MediaTek Inc.（联发科技）

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

Comments Accepted by ICCV 2025

2506.16572 2025-09-23 eess.IV cs.CV 79%

Single-step Diffusion for Image Compression at Ultra-Low Bitrates

Chanung Park, Joo Chan Lee, Jong Hwan Ko

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

2504.21476 2025-09-23 cs.CV cs.AI 79%

GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers

Xinyu Li, Qi Yao, Yuanda Wang

机构 * Shenfu Research（沈孚研究所）； Zhejiang University（浙江大学）

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

Comments The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025)

2503.09419 2025-09-23 cs.CV 79%

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space

Yifan Zhou, Zeqi Xiao, Shuai Yang, Xingang Pan

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室）； Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）

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

Comments Code is available at: https://github.com/SingleZombie/AFLDM

2509.16507 2025-09-23 cs.CV 79%

OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution

Hanting Li, Huaao Tang, Jianhong Han, Tianxiong Zhou, Jiulong Cui, Haizhen Xie, Yan Chen, Jie Hu

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2509.16429 2025-09-23 cs.CV 79%

TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks

Itzik Waizman, Yakov Gusakov, Itay Benou, Tammy Riklin Raviv

机构 * Ben-Gurion University of the Negev（本· Gurion 军事大学）

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

2509.16238 2025-09-23 q-bio.NC cs.GR 79%

Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment for Brain Connectome Modeling

Xiaoqi Sheng, Jiawen Liu, Jiaming Liang, Yiheng Zhang, Hongmin Cai

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

2508.15124 2025-09-23 cs.LG cs.CV 79%

Side Effects of Erasing Concepts from Diffusion Models

Shaswati Saha, Sourajit Saha, Manas Gaur, Tejas Gokhale

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

专题命中扩散模型：diffusion(title)；text-to-image(abstract)；分类 cs.CV

Comments Findings of the Association for Computational Linguistics: EMNLP 2025

2509.16106 2025-09-22 eess.IV cs.CV cs.LG 79%

PRISM: Probabilistic and Robust Inverse Solver with Measurement-Conditioned Diffusion Prior for Blind Inverse Problems

Yuanyun Hu, Evan Bell, Guijin Wang, Yu Sun

机构 * Johns Hopkins University（约翰霍普金斯大学）； Tsinghua University（清华大学）

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

2509.16091 2025-09-22 cs.CV 79%

Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising

Shen Cheng, Haipeng Li, Haibin Huang, Xiaohong Liu, Shuaicheng Liu

机构 * Dexmal ； UESTC ； Tele AI ； SJTU

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

2509.16019 2025-09-22 eess.IV cs.CV 79%

SLaM-DiMM: Shared Latent Modeling for Diffusion Based Missing Modality Synthesis in MRI

Bhavesh Sandbhor, Bheeshm Sharma, Balamurugan Palaniappan

机构 * IIT Bombay（印度理工学院班加罗尔分校）

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

2509.15553 2025-09-22 cs.CV cs.AI stat.AP 79%

Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification

Tian Lan, Yiming Zheng, Jianxin Yin

机构 * School of Statistics, Renmin University of China（中国人民大学统计学院）； Center for Applied Statistics and School of Statistics, Renmin University of China（中国人民大学应用统计中心和统计学院）

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

2509.13922 2025-09-22 cs.CV 79%

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification

Wenkui Yang, Jie Cao, Junxian Duan, Ran He

机构 * MAIS & NLPR, Institute of Automation, Chinese Academy of Sciences（自动化研究所、中国科学院）； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院、中国科学院大学）

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

Comments Accepted by ICCV 2025

2505.08437 2025-09-22 cs.CV 79%

TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection

Wenkui Yang, Zhida Zhang, Xiaoqiang Zhou, Junxian Duan, Jie Cao

机构 * MAIS \& NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China University of Science

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

Comments Accepted by PRCV 2024

2505.06793 2025-09-22 eess.IV cs.CV 79%

HistDiST: Histopathological Diffusion-based Stain Transfer

Erik Großkopf, Valay Bundele, Mehran Hosseinzadeh, Hendrik P. A. Lensch

机构 * University of Tübingen（图宾根大学）

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

Comments Accepted to DAGM GCPR 2025

2502.18104 2025-09-22 cs.CV 79%

PromptMID: Modal Invariant Descriptors Based on Diffusion and Vision Foundation Models for Optical-SAR Image Matching

Han Nie, Bin Luo, Jun Liu, Zhitao Fu, Huan Zhou, Shuo Zhang, Weixing Liu

机构 * State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（信息工程测绘与遥感国家重点实验室，武汉大学）

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

Comments 15 pages, 8 figures

Journal ref ISPRS2025

2410.14710 2025-09-22 cs.CV cs.AI cs.LG 79%

G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving

Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji

机构 * Sony AI（索尼人工智能）； Stanford University（斯坦福大学）； Sony Group Corporation（索尼集团）

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

2509.15220 2025-09-19 cs.CV 79%

Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model

Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys

机构 * Department of Computer Science, ETH Zurich（苏黎世联邦理工学院计算机科学系）； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机科学与数据科学学院）； Center for Frontier AI Research, Institute of High Performance Computing, A*STAR（A*STAR前沿人工智能研究中心，高性能计算研究所）； Microsoft, Zurich（微软（瑞士））

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

Comments Accepted to IEEE T-PAMI 2025. Code: https://github.com/cvg/diffmvs

2509.14755 2025-09-19 cs.CV 79%

Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks

Ahmed Sheta, Mathias Zinnen, Aline Sindel, Andreas Maier, Vincent Christlein

机构 * Pattern Recognition Lab, Friedrich-Alexander Universität Erlangen-Nürnberg, Germany（模式识别实验室，埃尔朗根-纽伦堡 Friedrich-Alexander 大学）

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

Comments Appeared at the 4th International Workshop on Fine Art Pattern Extraction and Recognition (FAPER 2025), in conjunction with ICIAP 2025; proceedings forthcoming in ICIAP 2025 Workshops (LNCS, Springer)

2509.14560 2025-09-19 cs.CV 79%

Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model

Zhaonan Wang, Manyi Li, ShiQing Xin, Changhe Tu

机构 * Shandong University（山东大学）

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

2411.17240 2025-09-19 cs.CV 79%

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

Junyuan Deng, Wei Yin, Xiaoyang Guo, Qian Zhang, Xiaotao Hu, Weiqiang Ren, Xiao-Xiao Long, Ping Tan

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； Horizon Robotics ； Nanjing University（南京大学）

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

2509.13768 2025-09-18 cs.CV 79%

Generative Image Coding with Diffusion Prior

Jianhui Chang

机构 * China Telecom Cloud Computing Research Institute（中国电信云计算研究院）

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

2509.13711 2025-09-18 cs.CV 79%

StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models

Qiuyu Tang, Joshua Krinsky, Aparna Bharati

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

2509.13525 2025-09-18 cs.CV cs.AI cs.LG 79%

ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors

Romain Hardy, Tyler Berzin, Pranav Rajpurkar

机构 * Department of Biomedical Informatics, Harvard Medical School（生物医学信息学系，哈佛医学院）； Center for Advanced Endoscopy, Beth Israel Deaconess Medical Center（先进内窥镜中心，贝塞斯达医院）

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

Comments 12 pages, 8 figures

2410.22454 2025-09-18 cs.CV 79%

Brain age identification from diffusion MRI synergistically predicts neurodegenerative disease

Chenyu Gao, Michael E. Kim, Karthik Ramadass, Praitayini Kanakaraj, Aravind R. Krishnan, Adam M. Saunders, Nancy R. Newlin, Ho Hin Lee, Qi Yang, Warren D. Taylor, Brian D. Boyd, Lori L. Beason-Held, Susan M. Resnick, Lisa L. Barnes, David A. Bennett, Marilyn S. Albert, Katherine D. Van Schaik, Derek B. Archer, Timothy J. Hohman, Angela L. Jefferson, Ivana Išgum, Daniel Moyer, Yuankai Huo, Kurt G. Schilling, Lianrui Zuo, Shunxing Bao, Nazirah Mohd Khairi, Zhiyuan Li, Christos Davatzikos, Bennett A. Landman

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

Comments Accepted to Imaging Neuroscience

2501.18834 2025-09-17 eess.IV cs.AI cs.CV 79%

Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential

Chenyu Gao, Kaiwen Xu, Michael E. Kim, Lianrui Zuo, Zhiyuan Li, Derek B. Archer, Timothy J. Hohman, Ann Zenobia Moore, Luigi Ferrucci, Lori L. Beason-Held, Susan M. Resnick, Christos Davatzikos, Jerry L. Prince, Bennett A. Landman

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

Comments Accepted to Computers in Biology and Medicine

2509.12239 2025-09-17 cs.LG cs.CV 79%

InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation

Sanyam Jain, Khuram Naveed, Illia Oleksiienko, Alexandros Iosifidis, Ruben Pauwels

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

2509.11724 2025-09-16 cs.LG cs.CV 79%

DRAG: Data Reconstruction Attack using Guided Diffusion

Wa-Kin Lei, Jun-Cheng Chen, Shang-Tse Chen

机构 * Research Center for Information Technology Innovation, Academia Sinica（中国科学院信息科技创新研究中心）； National Taiwan University（国立台湾大学）

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

Comments ICML 2025

1. 扩散模型 70196 篇

When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration

PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion

DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance

Single-step Diffusion for Image Compression at Ultra-Low Bitrates

GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space

OS-DiffVSR: Towards One-step Latent Diffusion Model for High-detailed Real-world Video Super-Resolution

TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks

Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment for Brain Connectome Modeling

Side Effects of Erasing Concepts from Diffusion Models

PRISM: Probabilistic and Robust Inverse Solver with Measurement-Conditioned Diffusion Prior for Blind Inverse Problems

Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising

SLaM-DiMM: Shared Latent Modeling for Diffusion Based Missing Modality Synthesis in MRI

Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification

Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification

TT-DF: A Large-Scale Diffusion-Based Dataset and Benchmark for Human Body Forgery Detection

HistDiST: Histopathological Diffusion-based Stain Transfer

PromptMID: Modal Invariant Descriptors Based on Diffusion and Vision Foundation Models for Optical-SAR Image Matching

G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving

Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Model

Data Augmentation via Latent Diffusion Models for Detecting Smell-Related Objects in Historical Artworks

Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

Generative Image Coding with Diffusion Prior

StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models

ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors

Brain age identification from diffusion MRI synergistically predicts neurodegenerative disease

Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential

InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation

DRAG: Data Reconstruction Attack using Guided Diffusion