Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

Han Gong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Downloads (Pure)

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 × 32 thumbnail input image. Our unoptimized Python implementation takes 1 ms/image, which is arguably 3-3750× 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.
Original languageEnglish
Title of host publicationBritish Machine Vision Conference (BMVC) 2019
PublisherBMVA Press
Publication statusPublished - Sep 2019
EventBritish Machine Vision Conference -
Duration: 9 Sep 201912 Sep 2019

Conference

ConferenceBritish Machine Vision Conference
Period9/09/1912/09/19

Keywords

  • illuminant estimation
  • convolution

Cite this