← 研踪 PaperTrailarXiv:2611.20854 · v1
When Is the Expensive Method Worth It? A Content-Driven Analysis of Classical Bayer Demosaicing
首次提交 2026-11-16 18:28
版本更新 2026-11-16 18:28
雷达观测 2026-11-17 17:11
摘要
Demosaicing reconstructs a full-colour image from a single-sensor colour-filter-array (CFA) mosaic, where only one colour is measured per pixel. Classical methods make different assumptions about images, from simple averaging to directional edge-aware interpolation, and the directional methods cost markedly more compute. We ask a practical question that a per-image quality ranking does not answer: for a given image, is the expensive directional method worth its cost? Using a controlled simulate-reconstruct pipeline on 80 benchmark images from four public datasets (Kodak, McMaster, BSD100, Urban100), six classical methods, and image-content descriptors fixed before any results were seen, we show that the quality gain of the edge-aware method (Menon 2007) over the best cheap linear method is not constant. It ranges from to dB, and on 31% of images it is zero or negative, meaning a cheap method matches or beats the expensive one. The gain is also predictable from content: it correlates with mean image saturation at (). We then build an interpretable depth-2 decision tree that recommends the best cheap method from image descriptors, beating an always-pick-the-most-common baseline by 20.0 percentage points under leave-one-image-out validation. The analysis uses no deep learning, and every step can be inspected.
作者备注:Preprint. 14 pages
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 18:28 · 最新观测版本
When Is the Expensive Method Worth It? A Content-Driven Analysis of Classical Bayer Demosaicing
Demosaicing reconstructs a full-colour image from a single-sensor colour-filter-array (CFA) mosaic, where only one colour is measured per pixel. Classical methods make different assumptions about images, from simple averaging to directional edge-aware interpolation, and the directional methods cost markedly more compute. We ask a practical question that a per-image quality ranking does not answer: for a given image, is the expensive directional method worth its cost? Using a controlled simulate-reconstruct pipeline on 80 benchmark images from four public datasets (Kodak, McMaster, BSD100, Urban100), six classical methods, and image-content descriptors fixed before any results were seen, we show that the quality gain of the edge-aware method (Menon 2007) over the best cheap linear method is not constant. It ranges from to dB, and on 31% of images it is zero or negative, meaning a cheap method matches or beats the expensive one. The gain is also predictable from content: it correlates with mean image saturation at (). We then build an interpretable depth-2 decision tree that recommends the best cheap method from image descriptors, beating an always-pick-the-most-common baseline by 20.0 percentage points under leave-one-image-out validation. The analysis uses no deep learning, and every step can be inspected.
查看此版本解读 →查看此版本原文 ↗