图像生成

2509.05625 2025-09-09 cs.CV 88%

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models

Kien Nguyen, Anh Tran, Cuong Pham

机构 * Qualcomm AI Research（高通人工智能研究）

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

2408.12528 2025-09-09 cs.CV 81%

Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, Mike Zheng Shou

机构 * Show Lab, National University of Singapore（新加坡国立大学Show实验室）； ByteDance（字节跳动）

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

Comments ICLR 2025

2403.01489 2025-09-09 cs.CV cs.AI 79%

Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models

Meiling Li, Zhenxing Qian, Xinpeng Zhang

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

Comments The paper has been withdrawn by the authors because the proposed approach is currently undergoing optimization and improvement. We are refining the methodology to achieve more robust and convincing results, and a revised version will be submitted once the enhancements are completed

2506.07963 2025-09-09 cs.AI cs.CL cs.CV 57%

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards

Jixiang Hong, Yiran Zhang, Guanzhong Wang, Yi Liu, Ji-Rong Wen, Rui Yan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）； School of Computer Science（计算机科学学院）； Baidu Inc.（百度公司）； School of Computer Science, Wuhan University（武汉大学计算机学院）

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

2405.15154 2025-09-09 cs.AI cs.LG 50%

Online Prompt Pricing based on Combinatorial Multi-Armed Bandit and Hierarchical Stackelberg Game

Meiling Li, Hongrun Ren, Haixu Xiong, Zhenxing Qian, Xinpeng Zhang

专题命中文生图：text-to-image(abstract)

Comments The paper has been withdrawn by the authors because the current experimental results are not sufficiently reliable. Further optimization and refinement of the methodology are required before the work can be disseminated

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

2506.03164 2025-09-09 cs.LG 85%

Test-Time Scaling of Diffusion Models via Noise Trajectory Search

Vignav Ramesh, Morteza Mardani

机构 * Harvard University（哈佛大学）； NVIDIA（NVIDIA公司）

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

2509.06573 2025-09-09 cs.GR 83%

From Rigging to Waving: 3D-Guided Diffusion for Natural Animation of Hand-Drawn Characters

Jie Zhou, Linzi Qu, Miu-Ling Lam, Hongbo Fu

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

2212.03221 2025-09-09 cs.CV eess.IV 83%

ADIR: Adaptive Diffusion for Image Reconstruction

Shady Abu-Hussein, Tom Tirer, Raja Giryes

机构 * Tel Aviv University（特拉维夫大学）； Bar Ilan University（巴伊兰大学）

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

Comments Project page https://shadyabh.github.io/ADIR/

Journal ref BMVC 2025

2509.04145 2025-09-09 cs.GR cs.CV 81%

Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion

Dongliang Cao, Guoxing Sun, Marc Habermann, Florian Bernard

机构 * University of Bonn（波恩大学）； Max Planck Institute for Informatics（马克斯·普朗克研究所（信息学））

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

Comments Project webpage: https://vcai.mpi-inf.mpg.de/projects/HDA/

2509.06693 2025-09-09 cs.CV 79%

STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment

Xichen Xu, Yanshu Wang, Jinbao Wang, Qunyi Zhang, Xiaoning Lei, Guoyang Xie, Guannan Jiang, Zhichao Lu

机构 * Global Institute of Future Technology, Shanghai Jiao Tong University（未来技术全球研究院，上海交通大学）； School of Artificial Intelligence, Shenzhen University（人工智能学院，深圳大学）； Department of Intelligent Manufacturing, CATL（智能制造部门，CATL）； Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）

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

2509.06579 2025-09-09 cs.CV 79%

CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis

Xin Kong, Daniel Watson, Yannick Strümpler, Michael Niemeyer, Federico Tombari

机构 * Imperial College London（伦敦帝国学院）； Google DeepMind（谷歌DeepMind）； Google（谷歌）； Technical University of Munich（慕尼黑技术大学）

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

2507.13087 2025-09-09 cs.CV 79%

DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model

Han Zhang, Xiangde Luo, Yong Chen, Kang Li

机构 * West China Biomedical Big Data Center（西昌生物医学大数据中心）； West China Hospital（西昌医院）； Sichuan University（四川大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

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

2501.16714 2025-09-09 cs.CV cs.AI 79%

Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models

Huijie Liu, Jingyun Wang, Shuai Ma, Jie Hu, Xiaoming Wei, Guoliang Kang

机构 * Beihang University（北航大学）

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

Comments 8 pages,6 figures

2412.03355 2025-09-09 cs.CV 79%

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution

Qinwei Lin, Xiaopeng Sun, Yu Gao, Yujie Zhong, Dengjie Li, Zheng Zhao, Haoqian Wang

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）； Meituan Inc.（美团公司）

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

Comments Accepted to ACM MM2025

2403.19508 2025-09-09 eess.IV cs.CV cs.LG 79%

Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models

Grzegorz Skorupko, Richard Osuala, Zuzanna Szafranowska, Kaisar Kushibar, Vien Ngoc Dang, Nay Aung, Steffen E Petersen, Karim Lekadir, Polyxeni Gkontra

机构 * Barcelona Artificial Intelligence in Medicine Lab (BCN-AIM)（巴塞罗那人工智能在医学实验室（BCN-AIM））； Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Spain（数学与计算机科学系，巴塞罗那大学，西班牙）； Helmholtz Center Munich（海德堡研究中心慕尼黑）； Technical University of Munich（慕尼黑技术大学）； William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University London, Charterhouse Square, London, UK（威廉·哈维研究所，英国国家健康研究院巴特研究所，伦敦女王玛丽大学，查尔斯广场，伦敦，英国）； Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, West Smithfield, London, UK（巴特心脏中心，圣巴塞洛缪医院，巴特健康国家卫生信托，西史密斯菲尔德，伦敦，英国）； Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚高级研究与教育研究所（ICREA））

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

2509.05321 2025-09-09 cs.CV cs.AI 79%

A Dataset Generation Scheme Based on Video2EEG-SPGN-Diffusion for SEED-VD

Yunfei Guo, Tao Zhang, Wu Huang, Yao Song

机构 * Chengdu Techman Software Co., Ltd.（成都技漫软件有限公司）； Sichuan University（四川大学）

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

2509.01837 2025-09-09 cs.CV 79%

PractiLight: Practical Light Control Using Foundational Diffusion Models

Yotam Erel, Rishabh Dabral, Vladislav Golyanik, Amit H. Bermano, Christian Theobalt

机构 * Tel Aviv University（特拉维夫大学）； Max Planck Institute for Informatics（马克斯·普朗克信息研究所）

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

Comments Project page: https://yoterel.github.io/PractiLight-project-page/

2507.12103 2025-09-09 cs.CV cs.CY 79%

DeepShade: Enable Shade Simulation by Text-conditioned Image Generation

Longchao Da, Xiangrui Liu, Mithun Shivakoti, Thirulogasankar Pranav Kutralingam, Yezhou Yang, Hua Wei

机构 * Arizona State University（亚利桑那州立大学）

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

Comments 7pages, 4 figures

2503.19757 2025-09-09 cs.RO cs.CV 79%

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Zhi Hou, Tianyi Zhang, Yuwen Xiong, Haonan Duan, Hengjun Pu, Ronglei Tong, Chengyang Zhao, Xizhou Zhu, Yu Qiao, Jifeng Dai, Yuntao Chen

机构 * Shanghai AI Lab（上海人工智能实验室）； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）； MMLab, The Chinese University of Hong Kong（香港中文大学MMLab）； Peking University（北京大学）； SenseTime Research（商汤科技研究院）； Tsinghua University（清华大学）； HKISI, CAS（中国科学院香港中文大学研究所）

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

Comments Preprint; https://robodita.github.io; To appear in ICCV2025

2509.06949 2025-09-09 cs.CL 78%