SOTAVerified

LuminanceL1Loss: A loss function which measures percieved brightness and colour differences

2023-11-08Unverified0· sign in to hype

Dominic De Jonge

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

We introduce LuminanceL1Loss, a novel loss function designed to enhance the performance of image restoration tasks. We demonstrate its superiority over MSE when applied to the Retinexformer, BUIFD and DnCNN architectures. Our proposed LuminanceL1Loss leverages a unique approach by transforming images into grayscale and subsequently computing the MSE loss for both grayscale and color channels. Experimental results demonstrate that this innovative loss function consistently outperforms traditional methods, showcasing its potential in image denoising and other related tasks in image reconstruction. It demonstrates gains up to 4.7dB. The results presented in this study highlight the efficacy of LuminanceL1Loss for various image restoration tasks.

Tasks

Reproductions