arXiv Machine Learning By Ziyan Huang, Lang Wu, Hongji Wang, Yifei Liu, Dongliang Tang, Hongqiao Wang

Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions

Read the original on arXiv Machine Learning →

arXiv:2605. 24590v2 Announce Type: replace-cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jul 7

Realistic Compound-Lens Defocus Blur Synthesis

Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets.

Hugging Face Trending Papers
Jun 13

Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors

Zero-Shot Self-Supervised Learning (ZS-SSL) has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction, eliminating the reliance on fully-sampled external datasets. However, learning solely from a single under-sampled scan suffers from supervision scarcity and optimization instability, often leading to overfitting or artifacts.

Hugging Face Trending Papers
Jun 25

Enabling self-supervised learned primal dual with Noise2Inverse

X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While learned reconstruction methods such as the Learned Primal-Dual algorithm achieve strong performance, they typically rely on supervised training with access to ground-truth data, which is often unavailable in practice.

arXiv Machine Learning
Jun 26

Enabling self-supervised learned primal dual with Noise2Inverse

arXiv:2606. 26991v1 Announce Type: cross Abstract: X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete.

By Antti S\"allinen, Siiri Rautio, Santeri Kaupinm\"aki, Andreas Hauptmann