Diffusion Probabilistic Models (DPMs) have been recently utilized to deal with various blind image restoration (IR) tasks, where they have demonstrated outstanding performance in terms of perceptual quality. However, the task-specific nature of existing solutions and the excessive computational costs related to their training, make such models impractical and challenging to use for different IR tasks than those that were initially trained for. This hinders their wider adoption, especially by those who lack access to powerful computational resources and vast amount of training data. In this work we aim to address the above issues and enable the successful adoption of DPMs in practical IR-related applications. Towards this goal, we propose a modular diffusion probabilistic IR framework (DP-IR), which allows us to combine the performance benefits of existing pre-trained state-of-the-art IR networks and generative DPMs, while it requires only the additional training of a relatively small module (0.7M params) related to the particular IR task of interest. Moreover, the architecture of the proposed framework allows for a sampling strategy that leads to at least four times reduction of neural function evaluations without suffering any performance loss, while it can also be combined with existing acceleration techniques such as DDIM. We evaluate our model on four benchmarks for the tasks of burst JDD-SR, dynamic scene deblurring, and super-resolution. Our method outperforms existing approaches in terms of perceptual quality while it retains a competitive performance with respect to fidelity metrics.
Tackling Hallucination from Conditional Models for Medical Image Reconstruction with DynamicDPS
Hawkes Institute, University College London, UK Department of Medical Physics;Biomedical Engineering, University College London, UK Department of Computer Science, University College London, UK The University of Utah, USA, Centre for AI, DS\&AI, AstraZeneca, UK
Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis
Sichuan University(四川大学);Singapore University of Technology and Design(新加坡科技设计大学);The University of Adelaide(阿德莱德大学);Australian National University(澳大利亚国立大学)
Unsupervised Low-dose CT Reconstruction with One-way Conditional Normalizing Flows
School of Mathematical Sciences, Capital Normal University(首都师范大学数学学院);Centre for Mathematical Imaging Techniques, University of Liverpool(利物浦大学数学成像技术中心);Department of Mathematics and Statistics, University of Strathclyde(斯特拉思克莱德大学数学与统计学系)
RA-CMF: Region-Adaptive Conditional MeanFlow for CT Image Reconstruction
Biomedical Informatics(生物医学信息学);Data Science University of Alabama at Birmingham Birmingham, AL, United States(数据科学,阿拉巴马大学伯明翰分校,伯明翰,AL,美国);Computer Science Florida Polytechnic University Lakeland, FL, United States(计算机科学,佛罗里达理工学院,拉凯兰德,FL,美国)
Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
School of Computer and Big Data, Minjiang University(闽江学院计算机与大数据学院);School of Information, Renmin University of China(中国人民大学信息学院);RMIT University(皇家墨尔本理工大学);Victoria University(维多利亚大学)
Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction
Swiss Data Science Center (SDSC) in Paul Scherrer Institute (PSI)(瑞士数据科学中心(SDSC)在保罗·舍勒研究所(PSI));Swiss Data Science Center (SDSC) and ETH Zurich(瑞士数据科学中心(SDSC)和苏黎世联邦理工学院);Swiss Data Science Center (SDSC) and Paul Scherrer Institute (PSI)(瑞士数据科学中心(SDSC)和保罗·舍勒研究所(PSI))
Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction
University College London(伦敦大学学院);Atinary Technologies(Atinary科技公司);University of Bremen(不来梅大学);Korea Advanced Institute of Science and Technology(韩国科学技术院);Ajou University School of Medicine(亚洲大学医学院);The Chinese University of Hong Kong(香港中文大学)
3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation
The Children’s Hospital of Philadelphia, USA(美国费城儿童医院);Department of Architecture and Engineering, University of Parma, Italy(意大利帕尔马大学建筑与工程系);Department of Information Engineering and Matemathics, University of Siena, Italy(意大利锡耶纳大学信息工程与数学系);Media Integration and Communication Center (MICC), University of Florence, Italy(意大利佛罗伦萨大学媒体整合与通信中心);Idiap Research Institute, Switzerland(瑞士IDiap研究所);École Polytechnique Fédérale de Lausanne (EPFL), Switzerland(瑞士洛桑联邦理工学院);University of Pennsylvania, USA(美国宾夕法尼亚大学)
Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
Department of Mathematics and Systems Engineering(数学与系统工程系);Department of Biomedical Engineering & Science(生物医学工程与科学系);Florida Institute of Technology(佛罗里达理工学院);A. A. Martinos Center for Biomedical Imaging(A.A. Martinos生物医学成像中心);Massachusetts General Hospital/Harvard Medical School(麻省总医院/哈佛医学院);Department of Radiology(放射科);Embry-Riddle Aeronautical University(艾姆伯-里尔航空大学)
Conditional Evidence Reconstruction and Decomposition for Interpretable Multimodal Diagnosis
Department of Biomedical Engineering, New Jersey Institute of Technology(新泽西理工学院生物医学工程系);Department of Computer Science and Engineering, The University of Texas at Arlington(德克萨斯大学阿灵顿分校计算机科学与工程系);Department of Computer Science, Indiana University Indianapolis(印第安纳大学印第安纳波利斯分校计算机科学系);School of Computing, University of Georgia(佐治亚大学计算科学学院)
DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing
Institute of Information Science, Beijing Jiaotong University(信息科学学院,北京交通大学);Visual Intelligence +X International Cooperation Joint Laboratory of MOE(视觉智能+X国际合作联合实验室)
Generative-Model-Based Fully 3D PET Image Reconstruction by Conditional Diffusion Sampling
School of Biomedical Engineering and Imaging Sciences, King’s College London(伦敦国王学院生物医学工程与影像科学学院);Institute of Psychiatry, Psychology and Neuroscience, King’s College London(伦敦国王学院精神病学、心理学与神经科学研究所);King’s College London & Guy’s and St Thomas’ PET Centre(伦敦国王学院与盖伊和圣托马斯 PET 中心)