Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, instead drawing only a single sample from a Gaussian distribution from which to generate their solution. In this paper, we introduce a particle-filtering-based framework for a nonlinear exploration of the solution space in the initial stages of reverse SDE methods. Our proposed particle-filtering-based latent diffusion (PFLD) method and proposed problem formulation and framework can be applied to any diffusion-based solution for linear or nonlinear inverse problems. Our experimental results show that PFLD outperforms the SoTA solver PSLD on the FFHQ-1K and ImageNet-1K datasets on inverse problem tasks of super resolution, Gaussian debluring and inpainting.
LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization
CNRS(法国国家科学研究中心);Univ. Bordeaux(波尔多大学);INRIA(法国国家信息与自动化研究所);Bordeaux INP(波尔多国立高等工程技术学院);Heriot-Watt University(赫瑞瓦特大学);Maxwell Institute for Mathematical Sciences(麦克斯韦数学科学研究所)
Hardware-Efficient Guided Image Filtering For Multi-Label Problem
Nanjing University of Science and Technology(南京理工大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
Unmixing Optical Signals from Undersampled Volumetric Measurements by Filtering the Pixel Latent Variables
CERVO Brain Research Centre, Université Laval(拉瓦尔大学CERVO脑研究中心);Institute Intelligence and Data, Université Laval(拉瓦尔大学智能与数据研究所);Centre for Optics, Photonics and Lasers, Université Laval(拉瓦尔大学光学、光子学与激光中心);MILA-Québec AI Institute(MILA-魁北克人工智能研究所)
PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning
Autonomous Intelligent Systems, Computer Science Institute VI – Intelligent Systems(智能系统);Robotics, Center for Robotics(机器人学);the Lamarr Institute for Machine Learning(拉马尔机器学习研究所);Artificial Intelligence, University of Bonn, Germany(人工智能,波恩大学,德国)
Self-supervised learning of inverse problem solvers in medical imaging
Technion(以色列理工学院);University of Waterloo(滑铁卢大学)
在过去的几年里,基于深度学习的方法在解决医学成像中的逆问题方面取得了巨大的成功。在这项工作中,我们解决了以下问题:\textit{Given a set of measurements obtained from real imaging experiments, what is the best way to use a learnable model and the physics of the modality to solve the inverse problem and reconstruct the latent image?}标准的监督学习为基础的方法来解决这个问题,通过收集已知的潜像和它们相应的测量数据集。然而,由于缺乏适当大小的训练集的可用性,并且更一般地,由于测量“地面实况”潜像的固有困难,这些方法通常是不切实际的。鉴于此,我们提出了一种自监督的方法来训练医学成像中的逆模型,在对齐的数据的情况下。我们的方法只需要在训练时访问测量值和前向模型。我们展示了它的有效性,在加速磁共振成像(MRI)中出现的逆问题。