Towards Controllable Real Image Denoising with Camera Parameters

TL;DR

This paper presents a controllable image denoising framework that leverages camera parameters like ISO, shutter speed, and F-number to adaptively improve noise removal performance in deep learning models.

Contribution

It introduces a novel method to incorporate camera parameters into denoising networks, enabling adjustable noise removal based on camera settings.

Findings

Enhances denoising performance with camera parameter control.

Seamlessly integrates controllability into existing neural networks.

Improves adaptability to different noise levels and camera conditions.

Abstract

Recent deep learning-based image denoising methods have shown impressive performance; however, many lack the flexibility to adjust the denoising strength based on the noise levels, camera settings, and user preferences. In this paper, we introduce a new controllable denoising framework that adaptively removes noise from images by utilizing information from camera parameters. Specifically, we focus on ISO, shutter speed, and F-number, which are closely related to noise levels. We convert these selected parameters into a vector to control and enhance the performance of the denoising network. Experimental results show that our method seamlessly adds controllability to standard denoising neural networks and improves their performance. Code is available at https://github.com/OBAKSA/CPADNet.