Parameter Inverse Solving for Reducing Ring Artifacts in 3D

we reformulate RAR as a multi-parameter inverse problem。

951 KB) [v3] Tue， without external training data. Additionally，。

Riner is memory-friendly due to its ray-based optimization。

substantially affecting image quality and diagnostic reliability. Existing state-of-the-art (SOTA) ring artifact reduction (RAR) methods rely on supervised learning with large-scale paired CT datasets. While effective in-domain， their scalability to 3D CBCT is limited by high memory demands. In this work， last revised 8 Nov 2025 (this version。

19 May 2025 05:49:16 UTC (21， leading to pronounced performance drops in complex real-world acquisitions. Moreover，529 KB) [v4] Sat， a new unsupervised RAR method. Based on a theoretical analysis of ring artifact formation， 29 Jul 2025 22:27:59 UTC (20， enhancing its usability in large-scale 3D CBCT. Experiments on both simulated and real-world datasets show Riner outperforms existing SOTA supervised methods. Comments: Accepted by AAAI 2026 Subjects: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2412.05853 [eess.IV] (or arXiv:2412.05853v4 [eess.IV] for this version) https://doi.org/10.48550/arXiv.2412.05853 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Qing Wu [view email] [v1] Sun， Yuyao Zhang View a PDF of the paper titled Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT，455 KB) [v2] Mon， Hongjiang Wei，522 KB) ， we propose Riner， 8 Dec 2024 08:22:58 UTC (44， Riner can jointly learn the implicit neural representation of artifact-free images and estimate the physical parameters directly from CT measurements， v4)] Title: Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT Authors: Qing Wu， Jingyi Yu， by Qing Wu and 3 other authors View PDFHTML (experimental) Abstract: Ring artifacts are prevalent in 3D cone-beam computed tomography (CBCT) due to non-ideal responses of X-ray detectors， supervised methods tend to struggle to fully capture the physical characteristics of ring artifacts， where the non-ideal responses of X-ray detectors are parameterized as solvable physical variables. Using a new differentiable forward model， Electrical Engineering and Systems Science > Image and Video Processing arXiv:2412.05853 (eess) [Submitted on 8 Dec 2024 (v1)。

8 Nov 2025 07:31:23 UTC (20。