MG-SpaIR: Multi-Grade Sparse-Guided Implicit Representation for Training-Data-Free Image Restoration [0.03%]
MG-SpaIR：无训练数据的图像恢复的多级稀疏引导隐式表示法
Jianmin Liao,Lei Huang,Ronglong Fang et al.
Jianmin Liao et al.
MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a mul...
Product-of-Gaussian-mixture diffusion models for joint nonlinear MRI reconstruction [0.03%]
基于高斯混合乘积扩散模型的联合非线性MRI重建方法
Laurenz Nagler,Martin Zach,Thomas Pock
Laurenz Nagler
Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However, most existing methods rely on large networks with opaque time conditioning mechanisms an...
Mohammad Shifat-E-Rabbi,Naqib Sad Pathan,Shiying Li et al.
Mohammad Shifat-E-Rabbi et al.
Learning from point sets is an essential component in many computer vision and machine learning applications. Native, unordered, and permutation-invariant set structure space is challenging to model, particularly for point set classificatio...
Diffusion-Shock PDEs for Deep Learning on Position-Orientation Space [0.03%]
基于位置定向空间的深度学习扩散冲击偏微分方程模型
Finn M Sherry,Kristina Schaefer,Remco Duits
Finn M Sherry
We extend regularised diffusion-shock (RDS) filtering from Euclidean space R 2 (Schaefer and Weickert in J Math Imaging Vis 66:447-463, 2024. 10.1007/s10851-024-01175-0) to position-orientation space M 2 ≅ R 2 × S 1 . This h...
Connected Components on Lie Groups and Applications to Multi-Orientation Image Analysis [0.03%]
Lie群上的连通分支及其在多方向图像分析中的应用
Nicky J van den Berg,Olga Mula,Leanne Vis et al.
Nicky J van den Berg et al.
We develop and analyze a new algorithm to find the connected components of a compact set I from a Lie group G endowed with a left-invariant Riemannian distance. For a given δ > 0 , the algorithm finds the largest cover of I such that ...
CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping [0.03%]
基于深层展开的运动矫正定量R2*映射框架（CoRRECT）
Xiaojian Xu,Weijie Gan,Satya V V N Kothapalli et al.
Xiaojian Xu et al.
Quantitative MRI (qMRI) refers to a class of MRI methods for quantifying the spatial distribution of biological tissue parameters. Traditional qMRI methods usually deal separately with artifacts arising from accelerated data acquisition, in...
Antonin Chambolle,Claire Delplancke,Matthias J Ehrhardt et al.
Antonin Chambolle et al.
In this work, we propose a new primal-dual algorithm with adaptive step sizes. The stochastic primal-dual hybrid gradient (SPDHG) algorithm with constant step sizes has become widely applied in large-scale convex optimization across many sc...
Elisa Davoli,Rita Ferreira,Irene Fonseca et al.
Elisa Davoli et al.
Due to their ability to handle discontinuous images while having a well-understood behavior, regularizations with total variation (TV) and total generalized variation (TGV) are some of the best-known methods in image denoising. However, lik...
Kristina Schaefer,Joachim Weickert
Kristina Schaefer
We introduce regularised diffusion-shock (RDS) inpainting as a modification of diffusion-shock inpainting from our SSVM 2023 conference paper. RDS inpainting combines two carefully chosen components: homogeneous diffusion and coherence-enha...
Fabian Parzer,Clemens Kirisits,Otmar Scherzer
Fabian Parzer
We consider the problem of blob detection for uncertain images, such as images that have to be inferred from noisy measurements. Extending recent work motivated by astronomical applications, we propose an approach that represents the uncert...