图像生成

2509.18796 2025-09-24 cs.CV 83%

Towards Application Aligned Synthetic Surgical Image Synthesis

Danush Kumar Venkatesh, Stefanie Speidel

机构 * Department of Translational Surgical Oncology, NCT/UCC Dresden（转化外科肿瘤学系）； DKFZ, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden,HZDR, Germany（德累斯顿技术大学医学院）； The Centre for Tactile Internet with Human-in-the-Loop (CeTI), TUD Dresden（人机交互 tactile 网络中心）

专题命中文生图：image synthesis(title)；image generation(abstract)；diffusion(abstract)；分类 cs.CV

2509.04545 2025-09-24 cs.CV 83%

PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting

Linqing Wang, Ximing Xing, Yiji Cheng, Zhiyuan Zhao, Donghao Li, Tiankai Hang, Jiale Tao, Qixun Wang, Ruihuang Li, Comi Chen, Xin Li, Mingrui Wu, Xinchi Deng, Shuyang Gu, Chunyu Wang, Qinglin Lu

机构 * Tencent Hunyuan（腾讯文言）

专题命中文生图：text-to-image(title,abstract)；diffusion(abstract)；分类 cs.CV

Comments Technical Report. Project Page: https://hunyuan-promptenhancer.github.io/

2411.12389 2025-09-24 cs.CR 82%

Combinational Backdoor Attack against Customized Text-to-Image Models

Wenbo Jiang, Jiaming He, Hongwei Li, Rui Zhang, Hanxiao Chen, Meng Hao, Haomiao Yang, Qingchuan Zhao, Guowen Xu

专题命中文生图：text-to-image(title,abstract)；diffusion(abstract)

2509.19203 2025-09-24 cs.CV 57%

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

Ioanna Ntinou, Alexandros Xenos, Yassine Ouali, Adrian Bulat, Georgios Tzimiropoulos

机构 * Queen Mary University of London（伦敦女王大学）； Samsung AI Centre（三星人工智能中心）； Technical University of Iași（伊阿苏技术大学）

专题命中文生图：text-to-image(abstract)；分类 cs.CV

Comments Accepted at EMNLP 2025

2504.20690 2025-09-24 cs.CV 88%

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, Yi Yang

机构 * ReLER, CCAI, Zhejiang University（研发实验室、中国人工智能学会、浙江大学）； DBMI, HMS, Harvard University（生物医学信息研究所、哈佛医学院、哈佛大学）

专题命中图像编辑：diffusion(title,abstract)；image editing(title,abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025, there will be future updates for camera ready version. Code: https://github.com/River-Zhang/ICEdit

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)

2509.16968 2025-09-24 cs.CV 83%

Penalizing Boundary Activation for Object Completeness in Diffusion Models

Haoyang Xu, Tianhao Zhao, Sibei Yang, Yutian Lin

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院）； School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）

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

2508.03485 2025-09-24 cs.CV 83%

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation

Lianwei Yang, Haokun Lin, Tianchen Zhao, Yichen Wu, Hongyu Zhu, Ruiqi Xie, Zhenan Sun, Yu Wang, Qingyi Gu

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）； School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）； Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）

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

2509.19296 2025-09-24 cs.CV cs.GR 81%

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Sherwin Bahmani, Tianchang Shen, Jiawei Ren, Jiahui Huang, Yifeng Jiang, Haithem Turki, Andrea Tagliasacchi, David B. Lindell, Zan Gojcic, Sanja Fidler, Huan Ling, Jun Gao, Xuanchi Ren

机构 * NVIDIA ； University of Toronto（多伦多大学）； Vector Institute（向量研究所）； Simon Fraser University（西蒙弗雷泽大学）

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

Comments Project Page: https://research.nvidia.com/labs/toronto-ai/lyra/

2504.10716 2025-09-24 cs.CV 79%

SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Models

Stathis Galanakis, Alexandros Lattas, Stylianos Moschoglou, Bernhard Kainz, Stefanos Zafeiriou

机构 * Imperial College London（伦敦帝国学院）； FAU Erlangen–Nürnberg（埃森哲-纽伦堡大学）

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

2509.18917 2025-09-24 cs.CV cs.AI 79%

LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models

Amirhesam Aghanouri, Cristina Olaverri-Monreal

机构 * Johannes Kepler University Linz（约翰·凯撒大学林茨）； Department Intelligent Transport Systems（智能交通系统部门）

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

2509.18502 2025-09-24 cs.CV 79%

Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment

Wenjie Liu, Hongmin Liu, Lixin Zhang, Bin Fan

机构 * School of Intelligence Science and Technology, University of Science and Technology Beijing（智能科学与技术学院，科学技术大学）； Institute of Artificial Intelligence, University of Science and Technology Beijing（人工智能研究院，科学技术大学）

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

2509.17993 2025-09-24 cs.CV 79%

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu, Yuyang Yu, Zikai Huang, Yi Wang, Shengfeng He

机构 * South China University of Technology（南方科技大学）； Singapore Management University（新加坡国立管理学院）； Dongguan University of Technology（东莞大学）

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

Comments Accepted by NeurIPS 2025

2509.08908 2025-09-24 cs.CV 79%

Diffusion-Based Action Recognition Generalizes to Untrained Domains

Rogerio Guimaraes, Frank Xiao, Pietro Perona, Markus Marks

机构 * California Institute of Technology（加州理工学院）

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

Comments Project page: https://www.vision.caltech.edu/actiondiff. Code: https://github.com/frankyaoxiao/ActionDiff

2503.20429 2025-09-24 cs.CV 79%

Latent Beam Diffusion Models for Generating Visual Sequences

Guilherme Fernandes, Vasco Ramos, Regev Cohen, Idan Szpektor, João Magalhães

机构 * NOVA LINCS, NOVA School of Science and Technology（NOVA LINCS、NOVA科学与技术学校）

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

2502.19200 2025-09-24 cs.CV 79%

HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection

Zekang Weng, Jinjin Shi, Jinwei Wang, Zeming Han

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

Comments The paper is withdrawn owing to issues found in the experimental results

2406.10211 2025-09-24 cs.CV 79%

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

Bowen Song, Jason Hu, Zhaoxu Luo, Jeffrey A. Fessler, Liyue Shen

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

Journal ref Neural Information Processing Systems (NeurIPS), 2024

2406.02462 2025-09-24 cs.CV cs.AI 79%

Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems

Jason Hu, Bowen Song, Xiaojian Xu, Liyue Shen, Jeffrey A. Fessler

机构 * Department of Electrical and Computer Engineering University of Michigan（电气与计算机工程系华盛顿大学）

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

Journal ref Neural Information Processing Systems (NeurIPS), 2024

2509.19276 2025-09-24 stat.ML cs.LG stat.CO 78%

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Tim Y. J. Wang, O. Deniz Akyildiz

专题命中扩散模型：diffusion(title,abstract)

Comments Accepted at the 2nd Workshop on Frontiers in Probabilistic Inference: Sampling Meets Learning, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

2509.19234 2025-09-24 cs.LG eess.SP 78%

Stability and Generalization of Adversarial Diffusion Training

Hesam Hosseini, Ying Cao, Ali H. Sayed

机构 * School of Engineering, École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院工程学院）

专题命中扩散模型：diffusion(title,abstract)

2408.17390 2025-09-24 math.NA cs.NA 78%

High-order finite element methods for three-dimensional multicomponent convection-diffusion

Aaron Baier-Reinio, Patrick E. Farrell

专题命中扩散模型：diffusion(title,abstract)

2509.18928 2025-09-24 eess.AS 78%

Direct Preference Optimization for Speech Autoregressive Diffusion Models

Zhijun Liu, Dongya Jia, Xiaoqiang Wang, Chenpeng Du, Shuai Wang, Zhuo Chen, Haizhou Li

专题命中扩散模型：diffusion(title,abstract)

2509.18686 2025-09-24 cs.RO cs.LG 78%

Query-Centric Diffusion Policy for Generalizable Robotic Assembly

Ziyi Xu, Haohong Lin, Shiqi Liu, Ding Zhao

机构 * Department of Mechanical Engineering, Carnegie Mellon University（机械工程系，卡内基梅隆大学）

专题命中扩散模型：diffusion(title,abstract)

Comments 8 pages, 7 figures

2509.18676 2025-09-24 cs.RO cs.SY eess.SY 78%

3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space

Sangjun Noh, Dongwoo Nam, Kangmin Kim, Geonhyup Lee, Yeonguk Yu, Raeyoung Kang, Kyoobin Lee

机构 * School of Integrated Technology (SIT), Gwangju Institute of Science and Technology (GIST)（整合技术学院（SIT）、全州科学技术学院（GIST））

专题命中扩散模型：diffusion(title,abstract)

Comments 7 main scripts + 2 reference pages

2509.18603 2025-09-24 eess.AS cs.AI cs.SD 78%

SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering

Jiarui Hai, Mounya Elhilali

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）

专题命中扩散模型：diffusion(title,abstract)

2509.18164 2025-09-24 cs.LG 78%

DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns

Ranfei Chen, Ming Chen

机构 * Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（智能信息处理重点实验室，计算技术研究所，中国科学院，北京，中国）； Computer Network Information Center, Chinese Academy of Sciences, Beijing, China（计算机网络信息中心，中国科学院，北京，中国）

专题命中扩散模型：diffusion(title,abstract)

2509.18144 2025-09-24 cs.LG cs.AI 78%

AdaSTI: Conditional Diffusion Models with Adaptive Dependency Modeling for Spatio-Temporal Imputation

Yubo Yang, Yichen Zhu, Bo Jiang

专题命中扩散模型：diffusion(title,abstract)

Comments 9 pages

2504.19428 2025-09-24 math.PR q-bio.PE 78%

The Feller diffusion conditioned on a single ancestral founder

Conrad J. Burden, Robert C. Griffiths

专题命中扩散模型：diffusion(title,abstract)

Comments 45 pages, 7 figures. Minor typos corrected for the published version. The second order subscripts are difficult to read in the published version but easily legible in this version

Journal ref Theoretical Population Biology 166(2025)1-15

2502.17928 2025-09-24 cs.SI cs.AI cs.LG 78%

Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data

Hongyi Chen, Jingtao Ding, Xiaojun Liang, Yong Li, Xiao-Ping Zhang

机构 * Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School Tsinghua University Shenzhen China（深圳 ubiquitous 数据赋能关键实验室，深圳国际研究生院，清华大学，深圳，中国）； Department of Electronic Engineering Tsinghua University Beijing China（电子工程系，清华大学，北京，中国）； Pengcheng Laboratory Shenzhen China（鹏城实验室，深圳，中国）； Pengcheng Laboratory（鹏城实验室）； Tsinghua University（清华大学）

专题命中扩散模型：diffusion(title,abstract)

Comments CIKM 2025

2312.05204 2025-09-24 physics.flu-dyn 78%

Stoichiometry preservation and generalization of Bilger mixture fraction for non-premixed combustion with differential molecular diffusion

Haifeng Wang, Tianfang Xie

专题命中扩散模型：diffusion(title,abstract)

Comments There appears to be an error in the paper. Particularly, the Peters mixture fraction was incorrectly claimed to preserve stoichiometry. In fact, it does not preserve stoichiometry. Thus we request to withdraw this paper

1. 文生图 4 篇

Towards Application Aligned Synthetic Surgical Image Synthesis

PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting

Combinational Backdoor Attack against Customized Text-to-Image Models

Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions

2. 图像编辑 1 篇

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

3. 扩散模型 48 篇

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Penalizing Boundary Activation for Object Completeness in Diffusion Models

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

SpinMeRound: Consistent Multi-View Identity Generation Using Diffusion Models

LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models

Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

Diffusion-Based Action Recognition Generalizes to Untrained Domains

Latent Beam Diffusion Models for Generating Visual Sequences

HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection

DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction

Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problems

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Stability and Generalization of Adversarial Diffusion Training

High-order finite element methods for three-dimensional multicomponent convection-diffusion

Direct Preference Optimization for Speech Autoregressive Diffusion Models

Query-Centric Diffusion Policy for Generalizable Robotic Assembly

3D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space

SynSonic: Augmenting Sound Event Detection through Text-to-Audio Diffusion ControlNet and Effective Sample Filtering

DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns

AdaSTI: Conditional Diffusion Models with Adaptive Dependency Modeling for Spatio-Temporal Imputation

The Feller diffusion conditioned on a single ancestral founder

Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data

Stoichiometry preservation and generalization of Bilger mixture fraction for non-premixed combustion with differential molecular diffusion