arXiv:2508. 10555v2 Announce Type: replace-cross Abstract: In this study, we extend the contrast source inversion to a fully differentiable, unsupervised framework based on a neural implicit representation of the contrast source.
arXiv:2609.25429v1 Announce Type: new Abstract: In this paper, we introduce the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR), an advanced variational paradigm that...
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.
arXiv:2609.12953v1 Announce Type: new Abstract: Flow matching approaches to imaging inverse problems commonly incorporate measurements in two ways. Conditioning-based approaches supply measurement-de...
This paper introduces a fully differentiable jitter correction technique for X‑ray phase‑contrast micro‑CT that uses a deep learning‑based image quality metric to estimate and compensate per‑projection rigid jitter directly from the acquired data, eliminating the need for a motion‑free reference scan. The method adapts a gradient‑based auto‑focus strategy to parallel‑beam geometry, benchmarks several objective functions, and validates the sensitivity of the visual information fidelity (VIF) metric to jitter artifacts. A compact 3D CNN predicts VIF scores from corrupted volumes, while a spatially selective total variation penalty suppresses spurious high‑frequency structures during optimization; experiments on biological specimens from multiple synchrotron beamlines confirm that the pipeline reliably restores fine structural detail across morphologically distinct samples.
The paper introduces CoSMo-RecNet, a modular framework for multi-contrast MRI reconstruction that operates effectively in low-data regimes. It leverages a reusable content/style prior learned from large, unpaired multi-contrast image datasets, allowing a lightweight unrolled network to refine reconstructions using only a few task‑specific training samples. Experiments on low‑field 0.3 T and ultra‑low‑field 47 mT datasets demonstrate that CoSMo-RecNet outperforms parameter‑matched MoDL, classical reconstruction, transfer learning, and zero‑shot methods, achieving higher quality with as few as five training subjects.
arXiv:2606. 07675v1 Announce Type: cross Abstract: Smartphone telephoto cameras are approaching a "telephoto physics wall": as pixel pitches shrink toward sub-0.
arXiv:2608. 19860v1 Announce Type: new Abstract: Single-shot exposure correction aims to map an arbitrarily degraded image---whether under-exposed, over-exposed, or a spatial mixture of both---to a well-exposed output from a single capture.
arXiv:2607. 25576v1 Announce Type: new Abstract: Photoacoustic tomography (PAT) combines the optical absorption contrast of biological tissue with the spatial resolution of ultrasound, yet recovering the initial pressure distribution from sparse-view sensor measurements remains an ill-posed inverse problem.
arXiv:2608. 09382v1 Announce Type: cross Abstract: Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging.
arXiv:2608.30782v1 Announce Type: new Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realis...
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.
The paper tackles the inverse problem of recovering the initial pressure distribution in photoacoustic tomography (PAT) when nonlinear acoustic propagation and viscous attenuation are present. It models these effects with a nonlinear damped viscoelastic wave equation and proves well‑posedness of the forward problem. For the inverse problem, the authors establish existence, uniqueness, and local uniqueness results, and then propose a hybrid reconstruction framework that uses a convolutional neural network to generate an initial guess followed by a gradient‑free sequential quadratic Hamiltonian optimization to enforce the PDE dynamics. Numerical experiments show that this hybrid approach yields better reconstruction quality, contrast, and robustness than either time‑reversal or CNN‑only methods.