tomography op• 数据种类:image → image
• 调用:fullseye.apply(img, "tm_sinogram_denoise", a=0.5, b=0.5)(2-D 的模型是一张图 + 两个标量旋钮 a,b∈[0,1])
> 该算子的说明尚无译文,以下照原文给出。
Smooth the input sinogram along the ANGLE direction (rows). Neighbouring
projection angles view almost the same object, so angle-direction smoothing
is a genuine consistency prior that suppresses per-angle detector noise while
preserving the sinusoidal traces. `a` sets the angle-axis Gaussian sigma
(`a*4), b adds a gentle detector-axis sigma (b*1.5`). Output stays
a same-shape sinogram in [0,1].
• gallery2d_physics_alife_3d 族使用指南
• 示例数据目录(下载 URL / 许可证) —— 2-D 用 skimage.data(BSD/公有领域)加合成图,3-D 给出真实数据源(Stanford/PDS 等)的下载 URL。
• 算子来历与参考文献 —— 该算子族所依据的研究/方法出处。
• 算法的正典(作者・年份)与用途见上面的族使用指南。
• gallery2d_physics_alife_3d — py -3.11 examples/gallery2d_physics_alife_3d.py
image 作为输入)identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter
tomography)tm_radon_forward · tm_fbp_reconstruct · tm_sart_reconstruct · tm_backproject_unfiltered
*Provenance: ops.py — 2D 算子登记表。本条目由 tools/opdocs.py md 自动生成(请勿手工编辑)。*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.