arXiv cs.AI· Johannes B. Thalhammer, Patrick Ilg, Tina Dorosti, Sebastian Peterhansl, Theresa Hiu, Daniel Frey, Zijin Huang, Florian Schaff, Daniela Pfeiffer, Franz Pfeiffer·· 1 天前AI 评分19
基于学习的探测器间隙插值方法用于光子计数X射线成像
Learning-Based Interpolation of Detector Gaps in Photon-Counting X-ray Imaging
AI 导读
研究将 WGAN-GP 与 Pix2Pix 两种生成模型用于填充光子计数 X 射线成像中拼接探测器模块的物理间隙，通过掩码策略限制仅修改间隙像素并约束填充区域均值与分布。
正文 · 原文
Abstract:Image detectors assembled from tiled modules have physical gaps in the field of view that must be filled before downstream processing such as phase retrieval or tomographic reconstruction. Unlike natural-image inpainting, detector-gap interpolation must leave all other pixels unmodified and preserve the intensity statistics of the filled region, since even a small shift in mean intensity can cause ring artifacts after reconstruction. We adapted two generative models, a Wasserstein GAN with gradient penalty (WGAN-GP) and a conditional Pix2Pix model, to this task. We implemented a masking strategy that restricts all changes to the gap pixels and loss terms that constrain the mean intensity and the intensity distribution of the filled region. Both models were trained on nanoCT projections with simulated gaps and compared with linear interpolation, Navier--Stokes inpainting, and the deep image-inpainting network MADF, quantitatively on simulated gaps and visually on real detector gaps. WGAN-GP and Pix2Pix achieved the best perceptual similarity (LPIPS) and histogram distance and, apart from linear interpolation, the shortest inference time. Pix2Pix required about five times fewer training GPU-hours than WGAN-GP. Ablation studies showed that masking the network output contributes by far the most to plausible inpainting results. Applied to sinograms, Pix2Pix produced the most natural gap filling but improved the reconstruction only slightly compared with linear interpolation. The source code and the weights of the final Pix2Pix model are available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15614 [cs.CV] |
| (or arXiv:2611.15614v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15614 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Johannes Thalhammer [view email]
[v1]
Wed, 11 Nov 2026 15:31:56 UTC (10,343 KB)
来源：arXiv cs.AI · arxiv.org