Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation

Gong, Han (2019) Convolutional Mean: A Simple Convolutional Neural Network for Illuminant Estimation. In: British Machine Vision Conference (BMVC) 2019. BMVA Press.

Preview

PDF (BMVC_2019) - Published Version Download (8MB) | Preview

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.

Item Type:	Book Section
Uncontrolled Keywords:	illuminant estimation,convolution,computer vision and pattern recognition ,/dk/atira/pure/subjectarea/asjc/1700/1707
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Colour and Imaging Lab
Depositing User:	LivePure Connector
Date Deposited:	12 Sep 2019 23:52
Last Modified:	13 Sep 2022 00:43
URI:	https://ueaeprints.uea.ac.uk/id/eprint/72118
DOI:

Downloads

Actions (login required)

View Item