图像生成 - arXivDaily 专题

2303.16509 2023-05-23 cs.CV cs.GR 81%

HoloDiffusion: Training a 3D Diffusion Model using 2D Images

Animesh Karnewar, Andrea Vedaldi, David Novotny, Niloy Mitra

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

Comments CVPR 2023 conference; project page at: https://holodiffusion.github.io/

2212.04048 2023-05-22 cs.CV cs.GR 81%

Executing your Commands via Motion Diffusion in Latent Space

Xin Chen, Biao Jiang, Wen Liu, Zilong Huang, Bin Fu, Tao Chen, Jingyi Yu, Gang Yu

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

Comments 18 pages, 11 figures, conference

2211.09707 2023-05-17 cs.LG cs.CV cs.GR cs.HC cs.SD eess.AS 81%

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models

Simon Alexanderson, Rajmund Nagy, Jonas Beskow, Gustav Eje Henter

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

Comments 20 pages, 9 figures. Published in ACM ToG and presented at SIGGRAPH 2023

Journal ref ACM Trans. Graph. 42, 4 (August 2023), 20 pages

2305.05464 2023-05-10 cs.CV cs.MM 81%

Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer

Nisha Huang, Yuxin Zhang, Weiming Dong

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

2212.03293 2023-05-09 cs.CV cs.AI cs.GR cs.LG 81%

Diffusion-SDF: Text-to-Shape via Voxelized Diffusion

Muheng Li, Yueqi Duan, Jie Zhou, Jiwen Lu

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

Comments Accepted to CVPR 2023, project page: https://ttlmh.github.io/DiffusionSDF/

2301.11445 2023-05-03 cs.CV cs.GR 81%

3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

Biao Zhang, Jiapeng Tang, Matthias Niessner, Peter Wonka

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

Comments Accepted by SIGGRAPH 2023 (Journal Track), Project website: https://1zb.github.io/3DShape2VecSet/, Project demo: https://youtu.be/KKQsQccpBFk

2304.09383 2023-04-20 eess.IV cs.CV cs.GR 81%

Denoising Diffusion Medical Models

Pham Ngoc Huy, Tran Minh Quan

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

Comments Accepted to IEEE ISBI 2023

2304.02602 2023-04-06 cs.CV cs.AI cs.GR 81%

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Eric R. Chan, Koki Nagano, Matthew A. Chan, Alexander W. Bergman, Jeong Joon Park, Axel Levy, Miika Aittala, Shalini De Mello, Tero Karras, Gordon Wetzstein

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

Comments Project page: https://nvlabs.github.io/genvs

2304.01893 2023-04-05 cs.CV cs.GR cs.LG 81%

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Davis Rempe, Zhengyi Luo, Xue Bin Peng, Ye Yuan, Kris Kitani, Karsten Kreis, Sanja Fidler, Or Litany

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

Comments Conference on Computer Vision and Pattern Recognition (CVPR) 2023

2303.09604 2023-03-20 cs.CV cs.GR 81%

DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion

Maham Tanveer, Yizhi Wang, Ali Mahdavi-Amiri, Hao Zhang

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

Comments Project website: https://ds-fusion.github.io/

2211.08428 2023-03-09 eess.IV cs.CV cs.LG cs.MM 81%

CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming

Qihua Zhou, Ruibin Li, Song Guo, Peiran Dong, Yi Liu, Jingcai Guo, Zhenda Xu

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

2301.10047 2023-02-03 cs.GR cs.CV cs.HC cs.SD eess.AS eess.IV 81%

DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model

Fan Zhang, Naye Ji, Fuxing Gao, Yongping Li

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

Comments 13 pages, 3 figures

2302.00190 2023-02-02 cs.CV cs.GR 81%

Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation

Jingyu Hu, Ka-Hei Hui, Zhengzhe Liu, Ruihui Li, Chi-Wing Fu

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

Comments arXiv admin note: substantial text overlap with arXiv:2209.08725

2212.08526 2022-12-19 cs.CV cs.AI cs.GR 81%

Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models

Ziyi Chang, Edmund J. C. Findlay, Haozheng Zhang, Hubert P. H. Shum

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

2212.04248 2022-12-09 cs.GR cs.CV cs.SD eess.AS 81%

Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors

Zhentao Yu, Zixin Yin, Deyu Zhou, Duomin Wang, Finn Wong, Baoyuan Wang

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

Comments 16 pages

2212.02837 2022-12-07 cs.CV cs.GR cs.LG cs.RO 81%

Pretrained Diffusion Models for Unified Human Motion Synthesis

Jianxin Ma, Shuai Bai, Chang Zhou

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

2210.04628 2022-10-11 cs.CV cs.GR cs.LG 81%

Novel View Synthesis with Diffusion Models

Daniel Watson, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, Mohammad Norouzi

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

2209.14828 2022-10-11 cs.CV cs.AI cs.GR cs.LG 81%

Denoising Diffusion Probabilistic Models for Styled Walking Synthesis

Edmund J. C. Findlay, Haozheng Zhang, Ziyi Chang, Hubert P. H. Shum

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

2209.14916 2022-10-04 cs.CV cs.GR 81%

Human Motion Diffusion Model

Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, Amit H. Bermano

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

2209.08725 2022-09-20 cs.CV cs.GR 81%

Neural Wavelet-domain Diffusion for 3D Shape Generation

Ka-Hei Hui, Ruihui Li, Jingyu Hu, Chi-Wing Fu

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

2110.05948 2021-10-13 eess.SP cs.AI cs.CV cs.GR cs.LG cs.SD eess.AS eess.IV 81%

Denoising Diffusion Gamma Models

Eliya Nachmani, Robin San Roman, Lior Wolf

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

Comments arXiv admin note: substantial text overlap with arXiv:2106.07582

1210.0880 2021-06-09 cs.CV cs.CG cs.GR math.AP 81%

Schrödinger Diffusion for Shape Analysis with Texture

Jose A. Iglesias, Ron Kimmel

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

Comments Extended version of NORDIA'12 paper. Includes one more figure and appendix with proof

Journal ref ECCV 2012. Workshops and Demonstrations, Lecture Notes in Computer Science 7583, pp. 123-132, Springer, 2012

1712.01697 2017-12-06 cs.CV cs.GR cs.NE eess.IV 81%

Dialectical Multispectral Classification of Diffusion-Weighted Magnetic Resonance Images as an Alternative to Apparent Diffusion Coefficients Maps to Perform Anatomical Analysis

Wellington Pinheiro dos Santos, Francisco Marcos de Assis, Ricardo Emmanuel de Souza, Plínio Batista dos Santos Filho, Fernando Buarque de Lima Neto

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

Journal ref Computerized Medical Imaging and Graphics, v. 33, p. 442-460, 2009

1307.2818 2013-07-11 cs.MM cs.CV 81%

Anisotropic Diffusion for Details Enhancement in Multi-Exposure Image Fusion

Harbinder Singh, Vinay Kumar, Sunil Bhooshan

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

Comments 30 pages

Journal ref ISRN Signal Processing, vol. 2013, Article ID 928971, 18 pages, 2013

1305.0218 2013-05-02 cs.CV cs.MM 81%

Video Segmentation via Diffusion Bases

Dina Dushnik, Alon Schclar, Amir Averbuch

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

Comments 29 pages, 11 figures

2608.08734 2026-08-11 cs.CV 新提交 80%

IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

IDATA：用于无限制对抗迁移攻击的可扩展可逆扩散模型

Yi Pan, Jun-Jie Huang, Tianrui Liu, Zihan Chen, Lin Liu, Zhao Wentao

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

AI总结 IDATA是一种用于无限制对抗迁移攻击的内存高效扩散框架，通过可逆扩散模块与低频约束模块提升攻击性能，在多基准测试中优于现有方法，可用于评估深度视觉模型黑盒鲁棒性。

Comments Adversarial attack,Invertible diffusion model,Memory-efficient,Low-frequency

2608.06717 2026-08-10 cs.CV 新提交 80%

WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restoration

WaveFreqAnchor：用于无训练人脸修复的波结构锚定与频率校正扩散

Zelin Du, Wenjie Li, Zhengxue Wang, Juncheng Li, Cailing Wang, Guangwei Gao

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

AI总结本研究针对现有扩散模型人脸修复的结构漂移与保真度问题，提出无训练框架WaveFreqAnchor，通过ASWG、MWFI、SHE设计实现高质量人脸修复，性能优于现有方法。

Comments training-free wavelet-structural diffusion sampling framework for face restoration that improves structural stability, identity consistency, and real-world perceptual quality without task-specific fine-tuning

2511.12940 2026-07-28 cs.CV 版本更新 80%

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

循环自回归扩散：全局记忆与局部注意力相结合

Taiye Chen, Zihan Ding, Anjian Li, Christina Zhang, Zeqi Xiao, Yisen Wang, Chi Jin

机构 * Peking University（北京大学）； Princeton University（普林斯顿大学）； Nanyang Technological University（南洋理工大学）

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

AI总结研究针对超长视频生成中现有模型的不足，提出循环自回归扩散（RAD）框架，结合循环块与局部注意力，解决训练推理差距等问题，在相关数据集实验中展现出长视频生成的优越性。

Comments Published at ECCV 2026. Project page: https://yeyutaihan.github.io/recurrent-autoregressive-diffusion/

2404.00491 2026-07-22 cs.CV 版本更新 80%

Denoising Monte Carlo Renders with Diffusion Models

用扩散模型去噪蒙特卡洛渲染图

Vaibhav Vavilala, Rahul Vasanth, David Forsyth

机构 * UIUC（伊利诺伊大学香槟分校）

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

AI总结研究如何用扩散模型去噪蒙特卡洛渲染图，该方法可基于多种自然渲染信息，定量实验显示其在多采样率下与最优方法竞争，定性检查表明重建结果类似真实图像，有直阴影边界、弯曲镜面反射且无亮点。

Comments Code here: https://github.com/vibe007/denoising-monte-carlo-renders-with-diffusion-models 25 pages, 18 figures, 2 tables

Journal ref 2025 International Conference on 3D Vision (3DV), pp. 835-844, 2025

2607.11385 2026-07-14 eess.IV cs.CV 新提交 80%

Diffusion MRI preprocessing affects ADC estimation and automatic PI-RADS v2.1 classification in bi-parametric prostate MRI

扩散加权磁共振成像预处理影响双参数前列腺磁共振成像中表观扩散系数估计和自动PI-RADS v2.1分类

Christos Kanakis, Mathias Perslev, Tim Schakel, Silvia Ingala, Akshay Pai, Dennis Klomp, Chantal M. W. Tax

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

AI总结研究不同DWI预处理策略对前列腺MRI中ADC估计及PI-RADS分类的影响，通过对268个病例应用多种处理方法，比较不同算法下的ADC图，训练分类器预测PI-RADS分数，发现预处理可提升ADC图质量及分类预测能力。

Comments 19 pages, 10 figures, ISMRM Diffusion workshop 2025, ESMRMB 2025

1. 扩散模型 70082 篇

HoloDiffusion: Training a 3D Diffusion Model using 2D Images

Executing your Commands via Motion Diffusion in Latent Space

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models

Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer

Diffusion-SDF: Text-to-Shape via Voxelized Diffusion

3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

Denoising Diffusion Medical Models

Generative Novel View Synthesis with 3D-Aware Diffusion Models

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion

CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming

DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model

Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation

Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models

Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors

Pretrained Diffusion Models for Unified Human Motion Synthesis

Novel View Synthesis with Diffusion Models

Denoising Diffusion Probabilistic Models for Styled Walking Synthesis

Human Motion Diffusion Model

Neural Wavelet-domain Diffusion for 3D Shape Generation

Denoising Diffusion Gamma Models

Schrödinger Diffusion for Shape Analysis with Texture

Dialectical Multispectral Classification of Diffusion-Weighted Magnetic Resonance Images as an Alternative to Apparent Diffusion Coefficients Maps to Perform Anatomical Analysis

Anisotropic Diffusion for Details Enhancement in Multi-Exposure Image Fusion

Video Segmentation via Diffusion Bases

IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

WaveFreqAnchor: Wave-Structural Anchoring and Frequency Correction Diffusion for Training-Free Face Restoration

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

Denoising Monte Carlo Renders with Diffusion Models

Diffusion MRI preprocessing affects ADC estimation and automatic PI-RADS v2.1 classification in bi-parametric prostate MRI