restoration op• 数据种类:image → image
• 调用:fullseye.apply(img, "iv_backproject_superres", 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。
Single-image iterative back-projection super-resolution (Irani-Peleg).
Upscale to a higher grid, simulate the low-res observation by blurring and
downscaling, back-project the residual into the high grid, then downscale the
consistent estimate back to HxW. Net effect: high-frequency detail is boosted
(sharpening-by-consistency). `a` sets iterations n = 1 + round(a*4) (1..5);
`b` sets the back-projection step gain g = 0.5 + b (0.5..1.5).
• gallery2d_smoothing_rank 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_smoothing_rank — py -3.11 examples/gallery2d_smoothing_rank.py
image 作为输入)identity · gaussian · mean_box · bilateral · unsharp · median · min_filter · max_filter
restoration)xsk_inpaint · xsk_richardson_lucy · xsk_unwrap_phase · xcv_inpaint · xsk2_wiener · xcv3_inpaint_ns · iv_richardson_lucy · iv_wiener_deconv_spatial
*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.