# Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

Source: [Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation](<https://www.sota2.com/research/paper/68fa66ea1e209131cea131ee>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:01:21.007Z

Authors: Han Gong

Published: 2020-01-14T17:11:17.000Z

## Abstract

We present Convolutional Mean (CM) - a simple and fast convolutional neural network for illuminant estimation. Our proposed method only requires a small neural network model (1.1K parameters) and a 48 x 32 thumbnail input image. Our unoptimized Python implementation takes 1 ms/image, which is arguably 3-3750x faster than the current leading solutions with similar accuracy. Using two public datasets, we show that our proposed light-weight method offers accuracy comparable to the current leading methods' (which consist of thousands/millions of parameters) across several measures.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Color Correction on Proposed dataset aligned Mirrorless sensors 1.0 (test)](<https://www.sota2.com/research/sota/color-correction-on-proposed-dataset-aligned-mirrorless-sensors-1-0-test.md>): Color Correction; Proposed dataset aligned Mirrorless sensors 1.0 (test); dE00 Mean: 3.17.

- [Color Correction on Proposed dataset aligned Mobile sensors 1.0 (test)](<https://www.sota2.com/research/sota/color-correction-on-proposed-dataset-aligned-mobile-sensors-1-0-test.md>): Color Correction; Proposed dataset aligned Mobile sensors 1.0 (test); Delta E00 Mean: 3.16.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2001.04911>)

[PDF](<https://arxiv.org/pdf/2001.04911.pdf>)
