图像生成 - arXivDaily 专题

2503.04344 2025-09-25 cs.CV 85%

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang, Siyuan Liang, Yaning Tan, Zhaowei Chen, Linze Li, Ge Wu, Yuhao Chen, Shuheng Li, Zhenyu Zhao, Caihua Chen, Jiajun Liang, Yao Tang

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

2412.06028 2025-09-24 cs.CV 85%

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Shuning Chang, Pichao Wang, Jiasheng Tang, Fan Wang, Yi Yang

机构 * Zhejiang University（浙江大学）； Damo Academy, Alibaba Group（阿里达摩院）； Hupan Lab（虎斑实验室）

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

Comments 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

2505.11196 2025-09-23 cs.CV 85%

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

Yuang Ai, Qihang Fan, Xuefeng Hu, Zhenheng Yang, Ran He, Huaibo Huang

机构 * CASIA（中国科学院自动化研究所）； UCAS（中国科学技术大学）； ByteDance（字节跳动）

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

Comments NeurIPS 2025 Spotlight

2504.13499 2025-09-23 cs.CV 85%

U-Shape Mamba: State Space Model for faster diffusion

Alex Ergasti, Filippo Botti, Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi, Andrea Prati

机构 * University of Parma（帕尔马大学）； University of Siena（锡耶纳大学）

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

Comments Accepted at CVPR 2025 eLVM workshop. The code is here: https://github.com/ErgastiAlex/U-Shape-Mamba

2509.09610 2025-09-12 cs.CV cs.AI 85%

Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth

Daria Laslo, Efthymios Georgiou, Marius George Linguraru, Andreas Rauschecker, Sabine Muller, Catherine R. Jutzeler, Sarah Bruningk

机构 * ETH Zurich, 8092 Zurich, Switzerland - SIB Swiss Institue of Bioinformatics, 1015 Lausanne, Switzerland Department of Radiation Oncology, Inselspital, Bern University Hospital ； University of Bern, Switzerland Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Medical Center, Washington, DC 20010, United States University of California San Francisco, San Francisco, CA 94143, United States University Children's Hospital Zurich, 8008 Zurich, Switzerland

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

Comments 13 pages, 4 figures

2504.05815 2025-09-12 cs.CV cs.AI 85%

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models

Jiahao Chen, Yu Pan, Yi Du, Chunkai Wu, Lin Wang

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

2509.06068 2025-09-09 cs.CV 85%

Home-made Diffusion Model from Scratch to Hatch

Shih-Ying Yeh

机构 * National Tsing Hua University（国立清华大学）

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

2509.02000 2025-09-03 cs.CV 85%

Palette Aligned Image Diffusion

Elad Aharoni, Noy Porat, Dani Lischinski, Ariel Shamir

机构 * Hebrew University（希伯来大学）； Reichman University（雷赫曼大学）

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

Comments 14 pages, 19 figures

2508.15093 2025-08-26 cs.CV 85%

CurveFlow: Curvature-Guided Flow Matching for Image Generation

Yan Luo, Drake Du, Hao Huang, Yi Fang, Mengyu Wang

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

2508.14933 2025-08-22 cs.GR cs.AI cs.LG 85%

Inference Time Debiasing Concepts in Diffusion Models

Lucas S. Kupssinskü, Marco N. Bochernitsan, Jordan Kopper, Otávio Parraga, Rodrigo C. Barros

机构 * MALTA - Machine Learning Theory and Applications Lab（机器学习理论与应用实验室）； School of Technology, Pontifícia Universidade Católica do Rio Grande do Sul（技术学院，里约格朗德杜斯尔格斯天主教大学）

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

2508.13628 2025-08-21 cs.CV 85%

DiffIER: Optimizing Diffusion Models with Iterative Error Reduction

Ao Chen, Lihe Ding, Tianfan Xue

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

2508.14276 2025-08-21 cs.CV cs.AI 85%

Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning

Said Djafar Said, Torkan Gholamalizadeh, Mostafa Mehdipour Ghazi

机构 * Pioneer Centre for AI, Department of Computer Science, University of Copenhagen Research（先锋人工智能中心、计算机科学系、哥本哈根大学研究）

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

Comments MICCAI 2025 Workshop on Oral and Dental Image Analysis (ODIN)

2508.12718 2025-08-19 cs.CV 85%

Single-Reference Text-to-Image Manipulation with Dual Contrastive Denoising Score

Syed Muhmmad Israr, Feng Zhao

机构 * Department of Automation, School of Information Science and Technology, University of Science and Technology of China（自动化系、信息科学与技术学院、中国科学技术大学）

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

2507.20094 2025-08-19 cs.CV cs.AI cs.MA 85%

Local Prompt Adaptation for Style-Consistent Multi-Object Generation in Diffusion Models

Ankit Sanjyal

机构 * Fordham University（福特汉姆大学）

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

Comments 10 Pages,10 figures, pre-print

2506.13307 2025-08-15 cs.CV cs.AI 85%

Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images

Solène Debuysère, Nicolas Trouvé, Nathan Letheule, Olivier Lévêque, Elise Colin

机构 * Paris-Saclay University（巴黎-萨克雷大学）； ONERA - The French Aerospace Lab（法国航空航天实验室）

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

2507.10340 2025-08-05 cs.CV 85%

Text Embedding Knows How to Quantize Text-Guided Diffusion Models

Hongjae Lee, Myungjun Son, Dongjea Kang, Seung-Won Jung

机构 * Korea University（韩国大学）

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

Comments ICCV 2025

2403.08255 2025-07-23 cs.CV 85%

Make Me Happier: Evoking Emotions Through Image Diffusion Models

Qing Lin, Jingfeng Zhang, Yew-Soon Ong, Mengmi Zhang

机构 * Nanyang Technological University, Singapore（南洋理工大学，新加坡）； The University of Auckland, New Zealand（奥克兰大学，新西兰）； RIKEN AIP, Tokyo, Japan（日本东京理化学研究所AIP）

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

2507.15249 2025-07-22 cs.CV 85%

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers

Yanbing Zhang, Zhe Wang, Qin Zhou, Mengping Yang

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

Comments Accepted by ICCV 2025

2507.13401 2025-07-21 cs.CV cs.LG 85%

MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing

Shreya Kadambi, Risheek Garrepalli, Shubhankar Borse, Munawar Hyatt, Fatih Porikli

机构 * Qualcomm AI Research（高通人工智能研究）

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

Comments 26 pages

2412.09626 2025-07-14 cs.CV 85%

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

Haonan Qiu, Shiwei Zhang, Yujie Wei, Ruihang Chu, Hangjie Yuan, Xiang Wang, Yingya Zhang, Ziwei Liu

机构 * Nanyang Technological University（南洋理工大学）； Alibaba Group（阿里巴巴集团）； Fudan University（复旦大学）

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

Comments ICCV 2025, Project Page: http://haonanqiu.com/projects/FreeScale.html, Code Repo: https://github.com/ali-vilab/FreeScale

2507.06033 2025-07-09 cs.CV cs.AI cs.LG 85%

TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision

Syeda Anshrah Gillani, Mirza Samad Ahmed Baig, Osama Ahmed Khan, Shahid Munir Shah, Umema Mujeeb, Maheen Ali

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

Comments 30 pages

2507.03846 2025-07-08 cs.CV cs.LG 85%

Interpretable Diffusion Models with B-cos Networks

Nicola Bernold, Moritz Vandenhirtz, Alice Bizeul, Julia E. Vogt

机构 * Department of Computer Science, ETH Zürich, Switzerland（苏黎世联邦理工学院计算机科学系）

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

2507.00992 2025-07-03 cs.CV 85%

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

Yuanrui Wang, Cong Han, Yafei Li, Zhipeng Jin, Xiawei Li, SiNan Du, Wen Tao, Yi Yang, Shuanglong Li, Chun Yuan, Liu Lin

机构 * Tsinghua University（清华大学）； Baidu Inc.（百度公司）

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

Comments Accepted by ICCV 2025

2410.10105 2025-07-01 cs.CV 85%

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

Qian Yu, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Bo Li, Lihe Zhang, Huchuan Lu

机构 * Dalian University of Technology（大连理工大学）； vivo Mobile Communication Co., Ltd（vivo移动通信有限公司）

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

Comments Published as a conference paper at ICLR 2025

2506.10633 2025-06-13 cs.CV 85%

Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models

Konstantinos Vilouras, Ilias Stogiannidis, Junyu Yan, Alison Q. O'Neil, Sotirios A. Tsaftaris

机构 * University of Edinburgh（爱丁堡大学）； Canon Medical Research Europe Ltd.（佳能医疗欧洲有限公司）

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

Comments 14 pages, 6 figures

2407.17493 2025-06-10 cs.CV cs.AI 85%

Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling

Youngseok Yoon, Dainong Hu, Iain Weissburg, Yao Qin, Haewon Jeong

机构 * UCSB California, USA（加州大学圣芭芭拉分校）

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

Comments version 3, additional 34 pages

2505.23283 2025-05-30 cs.CV 85%

RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries

Zhihong Tan, Jiayi Wang, Huiying Shi, Binyuan Huang, Hongchen Wei, Zhenzhong Chen

机构 * Zhihong Tan（谭志宏）； Jiayi Wang（王佳毅）； Huiying Shi（Shi 希慧）； Binyuan Huang（黄彬远）； Hongchen Wei（韦宏晨）； Zhenzhong Chen（陈振中）

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

2505.13740 2025-05-27 cs.LG cs.AI cs.CV 85%

Improving Compositional Generation with Diffusion Models Using Lift Scores

Chenning Yu, Sicun Gao

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

Journal ref ICML 2025

2501.18865 2025-05-26 cs.CV cs.AI cs.LG 85%

REG: Rectified Gradient Guidance for Conditional Diffusion Models

Zhengqi Gao, Kaiwen Zha, Tianyuan Zhang, Zihui Xue, Duane S. Boning

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

Comments 20 pages, 10 figures; accepted by ICML'25

2505.12486 2025-05-20 cs.CV 85%

Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation

Sangmin Jung, Utkarsh Nath, Yezhou Yang, Giulia Pedrielli, Joydeep Biswas, Amy Zhang, Hassan Ghasemzadeh, Pavan Turaga

机构 * Arizona State University（亚利桑那州立大学）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）

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

Comments Accepted in CVPR Workshop GMCV 2025

1. 扩散模型 70082 篇

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

U-Shape Mamba: State Space Model for faster diffusion

Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models

Home-made Diffusion Model from Scratch to Hatch

Palette Aligned Image Diffusion

CurveFlow: Curvature-Guided Flow Matching for Image Generation

Inference Time Debiasing Concepts in Diffusion Models

DiffIER: Optimizing Diffusion Models with Iterative Error Reduction

Tooth-Diffusion: Guided 3D CBCT Synthesis with Fine-Grained Tooth Conditioning

Single-Reference Text-to-Image Manipulation with Dual Contrastive Denoising Score

Local Prompt Adaptation for Style-Consistent Multi-Object Generation in Diffusion Models

Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images

Text Embedding Knows How to Quantize Text-Guided Diffusion Models

Make Me Happier: Evoking Emotions Through Image Diffusion Models

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers

MADI: Masking-Augmented Diffusion with Inference-Time Scaling for Visual Editing

FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion

TextPixs: Glyph-Conditioned Diffusion with Character-Aware Attention and OCR-Guided Supervision

Interpretable Diffusion Models with B-cos Networks

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

Anatomy-Grounded Weakly Supervised Prompt Tuning for Chest X-ray Latent Diffusion Models

Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling

RSFAKE-1M: A Large-Scale Dataset for Detecting Diffusion-Generated Remote Sensing Forgeries

Improving Compositional Generation with Diffusion Models Using Lift Scores

REG: Rectified Gradient Guidance for Conditional Diffusion Models

Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation