The paper presents convergence guarantees for Plug-and-Play (PnP) image restoration algorithms that use annealed noise levels, covering both deterministic and stochastic methods. It identifies explicit nonconvex objectives linked to the final denoising level and proves that iterates become asymptotically stationary with respect to these objectives, without requiring a specific noise decay schedule. The authors validate their theory experimentally on tasks such as inpainting, super‑resolution, demosaicing, and tomography.
By Samuel Hurault
arXiv:2607. 25967v2 Announce Type: replace-cross Abstract: Singular Value Decomposition (SVD) underlies matrix factorisation tasks across many fields, with imaging applications demanding real-time processing.
By Christopher Hahne
arXiv:2507. 06764v5 Announce Type: replace-cross Abstract: In this work, we propose Fast Equivariant Imaging (FEI), a novel unsupervised learning framework to rapidly and efficiently train deep imaging networks without ground-truth data.
By Guixian Xu, Jinglai Li, Junqi Tang
arXiv:2609.18773v1 Announce Type: new
Abstract: Long-range infrared imaging frequently confronts dense target clusters whose diffraction-limited signatures merge into a single indistinguishable blob,...
By Mengze Xu, Zhu Liu, Weidong Sheng, Boyang Li, Yimian Dai, Ming-Ming Cheng, Jian Yang
arXiv:2508. 05321v4 Announce Type: replace-cross Abstract: Assume you encounter an inverse problem that shall be solved for a large number of data, but no ground-truth data is available.
By Laura Hellwege, Johann Christopher Engster, Moritz Schaar, Thorsten M. Buzug, Maik Stille
The paper introduces a highly efficient variational approximation for Gaussian Mixture Models (GMMs) with arbitrary covariances, integrated with mixtures of factor analyzers. This method reduces the per‑iteration runtime from ≠O(NCD^2) to a complexity that scales linearly with dimensionality D and sublinearly with the product NC. Experiments demonstrate sublinear scaling across the entire optimization, order‑of‑magnitude speed‑ups on large benchmarks, training of GMMs with over 10 billion parameters in under nine hours on a single CPU, and competitive zero‑shot image denoising performance.
By Sebastian Salwig, Till Kahlke, Florian Hirschberger, Dennis Forster, J\"org L\"ucke
arXiv:2608.23249v1 Announce Type: new
Abstract: We consider a multistatic radio-frequency imaging problem with anisotropy, in which the reflection from a point depends on the positions of the transmi...
By Amir Rezaei, Wen-Xin Pan, Giuseppe Caire
arXiv:2607. 10789v1 Announce Type: new Abstract: Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct reconstruction pipeline demands deep domain expertise and remains laborious even for domain scientists.
By Siyi Chen, Jiahe Ying, Yixuan Jia, Yuxuan Gu, Enze Ye, Weimin Bai, Zhijun Zeng, Shaochi Ren, Binhong Gao, Yubing Li, Tianhan Zhang, He Sun
arXiv:2608.29820v1 Announce Type: new
Abstract: Ultrasound B-mode imaging commonly suffers from speckle noise and artifacts, requiring a delicate balance between contrast, resolution, and preservatio...
By Juneyong Lee, Jaeyoung Choi
The paper introduces a physics‑guided, data‑driven framework for reconstructing dense ultrasound RF data from sparse acquisitions. It trains an end‑to‑end interpolation network with a hybrid RF‑ and beamforming‑domain loss, stabilized by exponential moving average, and employs random‑skip masking to generalize across varying sparsity patterns and channel configurations. On a held‑out test set, the method achieves a mean SSIM of about 0.95 across decimation factors from ×2 to ×13, consistently improving RF reconstruction and post‑beamforming image quality.
By Luoyuan Zhang, Yiyang You, Ananya Tandri, Yinan Feng, Hyunwoo Song, Jeeun Kang, Youzuo Lin
arXiv:2603. 17415v2 Announce Type: replace-cross Abstract: Image registration is an ill-posed dense vision task, where multiple solutions achieve similar loss values, motivating probabilistic inference.
By Ivor J. A. Simpson, Neill D. F. Campbell
arXiv:2603. 04438v3 Announce Type: replace-cross Abstract: Fully unsupervised deep generative modeling (FU-DGM) offers significant potential for compressively sampled magnetic resonance imaging (CS-MRI) reconstruction.
By Qingyong Zhu, Yumin Tan, Xiang Gu, Dong Liang