NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Datase

arXiv:2404.08514v1 Announce Type: new
Abstract: Despite the significant progress in image denoising, it is still challenging to restore fine-scale details while removing noise, especially in extremely low-light environments. Leveraging near-infrared (NIR) images to assist visible RGB image denoising shows the potential to address this issue, becoming a promising technology. Nonetheless, existing works still struggle with taking advantage of NIR information effectively for real-world image denoising, due to the content inconsistency between NIR-RGB images and the scarcity of real-world paired datasets. …

arxiv benchmark cs.cv denoising fusion image type world