LuminanceL1Loss: A loss function which measures percieved brightness and colour differences
This is an incremental improvement for image denoising and reconstruction tasks, potentially benefiting researchers and practitioners in computer vision.
The paper tackled image restoration by introducing LuminanceL1Loss, a loss function that measures perceived brightness and color differences, resulting in gains up to 4.7dB over traditional methods like MSE.
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.