图像生成 - arXivDaily 专题

2510.04125 2025-10-07 cs.CV 79%

Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation

Seunghyun Lee, Tae-Kyun Kim

机构 * KAIST（韩国科学技术院）

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

2510.04069 2025-10-07 cs.CV 79%

Diffusion Low Rank Hybrid Reconstruction for Sparse View Medical Imaging

Zongyin Deng, Qing Zhou, Yuhao Fang, Zijian Wang, Yao Lu, Ye Zhang, Chun Li

机构 * Shenzhen MSU-BIT University（深圳MSU-BIT大学）； China Media Group（中国媒体集团）； School of Mathematics and Statistics, Beijing Institute of Technology（北京理工大学数学与统计学院）

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

2510.03675 2025-10-07 cs.CV 79%

A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems

Siva Sai, Saksham Gupta, Vinay Chamola, Rajkumar Buyya

机构 * Department of Electrical and Electronics Engineering, BITS-Pilani, Pilani Campus（比特学院电子与电子工程系）； The Quantum Cloud Computing and Distributed Systems (qCLOUDS) Laboratory, School of Computing and Information Systems, The University of Melbourne（墨尔本大学计算机与信息系统学院量子云计算与分布式系统实验室）； qCLOUDS Laboratory（qCLOUDS实验室）

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

2510.03545 2025-10-07 cs.CV cs.RO 79%

SketchPlan: Diffusion Based Drone Planning From Human Sketches

Sixten Norelius, Aaron O. Feldman, Mac Schwager

机构 * EECS, KTH Royal Institute of Technology（皇家理工学院电子工程与计算机科学系）； Department of Aeronautics and Astronautics, Stanford University（斯坦福大学航空与航天系）

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

Comments Code available at https://github.com/sixnor/SketchPlan

2509.22728 2025-10-07 cs.SD cs.AI cs.MM eess.AS 79%

Prompt-aware classifier free guidance for diffusion models

Xuanhao Zhang, Chang Li

机构 * China Pharmaceutical University（中国药科大学）； University of Science and Technology of China（中国科学技术大学）

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

Comments 6 pages, 3 figures

2507.13934 2025-10-07 cs.CV 79%

DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization

Marzieh Gheisari, Auguste Genovesio

机构 * École Normale Supérieure PSL（巴黎高等师范学院）

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

2507.07510 2025-10-07 cs.CV cs.LG 79%

Divergence Minimization Preference Optimization for Diffusion Model Alignment

Binxu Li, Minkai Xu, Jiaqi Han, Meihua Dang, Stefano Ermon

机构 * Stanford University（斯坦福大学）

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

2505.23444 2025-10-07 cs.CV cs.AI 79%

CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis

Runmin Jiang, Genpei Zhang, Yuntian Yang, Siqi Wu, Minhao Wu, Wanyue Feng, Yizhou Zhao, Xi Xiao, Xiao Wang, Tianyang Wang, Xingjian Li, Muyuan Chen, Min Xu

机构 * Carnegie Mellon University（卡内基梅隆大学）； Stanford University（斯坦福大学）； Harvard University（哈佛大学）； University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）； Oak Ridge National Laboratory（橡树岭国家实验室）； University of Liverpool（利物浦大学）

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

2503.07120 2025-10-07 cs.CV cs.LG 79%

FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching

Zhen Zou, Feng Zhao

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

2510.03302 2025-10-07 cs.LG cs.CV 79%

Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models

Daiheng Gao, Nanxiang Jiang, Andi Zhang, Shilin Lu, Yufei Tang, Wenbo Zhou, Weiming Zhang, Zhaoxin Fan

机构 * USTC（中国科学技术大学）； Beihang University（北京航空航天大学）； University of Manchester（曼彻斯特大学）； NTU（南洋理工大学）； FYUST（福建师范大学）

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

Comments 21 pages, 10 figures

2510.03110 2025-10-06 cs.CV 79%

GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion

Beibei Lin, Tingting Chen, Robby T. Tan

机构 * National University of Singapore（新加坡国立大学）

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

Comments Accepted by NeurIPS 2025. Project page: https://bb12346.github.io/GeoComplete/

2510.01669 2025-10-06 cs.CV 79%

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

Jin Cao, Hongrui Wu, Ziyong Feng, Hujun Bao, Xiaowei Zhou, Sida Peng

机构 * State Key Lab of CAD&CG, Zhejiang University（CAD与CG国家重点实验室，浙江大学）； Tongji University（同济大学）； DeepGlint

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

Comments page: https://jin-cao-tma.github.io/UniVerse.github.io/ code: https://github.com/zju3dv/UniVerse

2411.18702 2025-10-06 cs.CV cs.AI cs.LG eess.IV 79%

Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models

Chicago Y. Park, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov

机构 * Washington University in St. Louis（华盛顿大学圣路易斯分校）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

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

Journal ref IEEE Signal Processing Magazine, vol. 42, no. 3, pp. 40-51, May 2025

2211.10655 2025-10-06 cs.CV cs.AI cs.LG 79%

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Hyungjin Chung, Dohoon Ryu, Michael T. McCann, Marc L. Klasky, Jong Chul Ye

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

Comments 14 pages, 10 figures

Journal ref 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 22542-22551

2209.14687 2025-10-06 stat.ML cs.AI cs.CV cs.LG 79%

Diffusion Posterior Sampling for General Noisy Inverse Problems

Hyungjin Chung, Jeongsol Kim, Michael T. Mccann, Marc L. Klasky, Jong Chul Ye

机构 * KAIST（韩国科学技术院）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

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

Comments ICLR 2023 spotlight

Journal ref The Eleventh International Conference on Learning Representations (ICLR) 2023

2510.02086 2025-10-03 cs.CV 79%

VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and Segmentation

Arman Behnam

机构 * College of Computing, Department of Computer Science（计算学院、计算机科学系）； Illinois Institute of Technology（伊利诺伊理工学院）

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

2510.01749 2025-10-03 physics.optics cs.CV 79%

Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models

Valentin Delchevalerie, Nicolas Roy, Arnaud Bougaham, Alexandre Mayer, Benoît Frénay, Michaël Lobet

机构 * University of Namur, Faculty of Computer Science（努尔大学计算机科学学院）； NaDI a & NaXys b institutes（NaDI机构及NaXys机构）； University of Namur, Department of Physics（努尔大学物理系）； NaXys a & NISM b institutes（NaXys机构及NISM机构）； Cenaero（Cenaero机构）

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

2510.01388 2025-10-03 cs.RO cs.CV 79%

VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation

Arthur Zhang, Xiangyun Meng, Luca Calliari, Dong-Ki Kim, Shayegan Omidshafiei, Joydeep Biswas, Ali Agha, Amirreza Shaban

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

Comments 9 pages, 6 figures, 3 tables

2509.17847 2025-10-03 cs.CV 79%

Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology

Saghir Alfasly, Wataru Uegami, MD Enamul Hoq, Ghazal Alabtah, H. R. Tizhoosh

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

Comments NeurIPS 2025

2508.17356 2025-10-03 cs.CV 79%

DiCache: Let Diffusion Model Determine Its Own Cache

Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Dahua Lin, Jiaqi Wang

机构 * Shanghai Jiao Tong University（上海交通大学）； University of Science and Technology of China（中国科学技术大学）； Fudan University（复旦大学）； The Chinese University of Hong Kong（香港中文大学）； Shanghai AI Laboratory（上海人工智能实验室）； Shanghai Innovation Institute（上海创新研究院）； CPII under InnoHK（InnoHK下的CPII）

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

Comments Project Page: https://bujiazi.github.io/dicache.github.io/ Code: https://github.com/Bujiazi/DiCache

2406.02842 2025-10-03 cs.CV 79%

DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

Paul Couairon, Mustafa Shukor, Jean-Emmanuel Haugeard, Matthieu Cord, Nicolas Thome

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

Comments NeurIPS 2024. Project page at https://diffcut-segmentation.github.io. Code at https://github.com/PaulCouairon/DiffCut

2306.04098 2025-10-03 cs.LG cs.CV 79%

Phoenix: A Federated Generative Diffusion Model

Fiona Victoria Stanley Jothiraj, Afra Mashhadi

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

2510.00527 2025-10-02 cs.CV 79%

Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation

Taeyun Woo, Jinah Park, Tae-Kyun Kim

机构 * KAIST（韩国科学技术院）

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

Comments 15 pages, 8 figures

2509.05978 2025-10-02 eess.IV cs.CL cs.CV cs.LG 79%

Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance

Mohamed Mohamed, Brennan Nichyporuk, Douglas L. Arnold, Tal Arbel

机构 * McGill University（麦吉尔大学）； Mila – Quebec AI Institute（魁北克人工智能研究所）

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

Comments Accepted to the 2025 MICCAI ELAMI Workshop

2506.18484 2025-10-02 eess.IV cs.CV 79%

GANs vs. Diffusion Models for virtual staining with the HER2match dataset

Pascal Klöckner, José Teixeira, Diana Montezuma, Jaime S. Cardoso, Hugo M. Horlings, Sara P. Oliveira

机构 * The Netherlands Cancer Institute, Amsterdam, The Netherlands（荷兰癌症研究所）； Faculty of Engineering, University of Porto, Porto, Portugal（葡萄牙波尔图大学工程学院）； IMP Diagnostics, Porto, Portugal（IMP诊断（葡萄牙波尔图））

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

2505.24210 2025-10-02 cs.CV cs.NA math.NA 79%

STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence

Zheng Tan, Weizhen Wang, Andrea L. Bertozzi, Ernest K. Ryu

机构 * Department of Mathematics, University of California, Los Angeles（数学系，加州大学洛杉矶分校）； Department of Computer Science, University of California, Los Angeles（计算机科学系，加州大学洛杉矶分校）

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

2505.20756 2025-10-02 eess.AS cs.MM cs.SD 79%

REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion

Ishan D. Biyani, Nirmesh J. Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik, Rajiv R. Shah

机构 * Indraprastha Institute of Information Technology (IIIT)（印度普拉斯塔信息技术学院）

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

Comments Accepted in INTERSPEECH 2025

Journal ref Proceeding of INTERSPEECH 2025

2504.10567 2025-10-02 cs.CV eess.IV 79%

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models

Yushu Wu, Yanyu Li, Ivan Skorokhodov, Anil Kag, Willi Menapace, Sharath Girish, Aliaksandr Siarohin, Yanzhi Wang, Sergey Tulyakov

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

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

Comments 17 pages, 6 figures, 9 tables

2410.18737 2025-10-02 cs.CV 79%

Rectified Diffusion Guidance for Conditional Generation

Mengfei Xia, Nan Xue, Yujun Shen, Ran Yi, Tieliang Gong, Yong-Jin Liu

机构 * Tsinghua University（清华大学）； Ant Group（蚂蚁集团）； Shanghai Jiao Tong University（上海交通大学）； Xi’an Jiao Tong University（西安交通大学）

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

2310.09469 2025-10-02 cs.CV 79%

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner

Mengfei Xia, Yujun Shen, Changsong Lei, Yu Zhou, Ran Yi, Deli Zhao, Wenping Wang, Yong-Jin Liu

机构 * Tsinghua University（清华大学）； Ant Group（蚂蚁集团）； Alibaba Group（阿里巴巴集团）； Shanghai Jiao Tong University（上海交通大学）； Texas A&M University（德克萨斯大学）

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

1. 扩散模型 70196 篇

Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation

Diffusion Low Rank Hybrid Reconstruction for Sparse View Medical Imaging

A Novel Cloud-Based Diffusion-Guided Hybrid Model for High-Accuracy Accident Detection in Intelligent Transportation Systems

SketchPlan: Diffusion Based Drone Planning From Human Sketches

Prompt-aware classifier free guidance for diffusion models

DiViD: Disentangled Video Diffusion for Static-Dynamic Factorization

Divergence Minimization Preference Optimization for Diffusion Model Alignment

CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis

FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Caching

Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models

GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Diffusion Posterior Sampling for General Noisy Inverse Problems

VGDM: Vision-Guided Diffusion Model for Brain Tumor Detection and Segmentation

Towards Photonic Band Diagram Generation with Transformer-Latent Diffusion Models

VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation

Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology

DiCache: Let Diffusion Model Determine Its Own Cache

DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut

Phoenix: A Federated Generative Diffusion Model

Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation

Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance

GANs vs. Diffusion Models for virtual staining with the HER2match dataset

STORK: Faster Diffusion And Flow Matching Sampling By Resolving Both Stiffness And Structure-Dependence

REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion

H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models

Rectified Diffusion Guidance for Conditional Generation

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner