LuminanceL1Loss: A loss function which measures percieved brightness and colour differences
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Color Image Restoration Exploiting Inter-channel Correlation with a 3-stage CNN
Single Stage Adaptive Multi-Attention Network for Image Restoration
Image Restoration via Frequency Selection
SAR Image Despeckling Using Continuous Attention Module
LangMamba: A Language-driven Mamba Framework for Low-dose CT Denoising with Vision-language Models
Energy-Based Transformers are Scalable Learners and Thinkers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.