Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation

04/18/2019
by   Ronnachai Jaroensri, et al.
10

Image reconstruction techniques such as denoising often need to be applied to the RGB output of cameras and cellphones. Unfortunately, the commonly used additive white noise (AWGN) models do not accurately reproduce the noise and the degradation encountered on these inputs. This is particularly important for learning-based techniques, because the mismatch between training and real world data will hurt their generalization. This paper aims to accurately simulate the degradation and noise transformation performed by camera pipelines. This allows us to generate realistic degradation in RGB images that can be used to train machine learning models. We use our simulation to study the importance of noise modeling for learning-based denoising. Our study shows that a realistic noise model is required for learning to denoise real JPEG images. A neural network trained on realistic noise outperforms the one trained with AWGN by 3 dB. An ablation study of our pipeline shows that simulating denoising and demosaicking is important to this improvement and that realistic demosaicking algorithms, which have been rarely considered, is needed. We believe this simulation will also be useful for other image reconstruction tasks, and we will distribute our code publicly.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 7

page 8

research
06/02/2022

Modeling sRGB Camera Noise with Normalizing Flows

Noise modeling and reduction are fundamental tasks in low-level computer...
research
01/30/2022

Practical Noise Simulation for RGB Images

This document describes a noise generator that simulates realistic noise...
research
08/04/2021

Physics-based Noise Modeling for Extreme Low-light Photography

Enhancing the visibility in extreme low-light environments is a challeng...
research
04/03/2022

Estimating Fine-Grained Noise Model via Contrastive Learning

Image denoising has achieved unprecedented progress as great efforts hav...
research
11/27/2018

Unprocessing Images for Learned Raw Denoising

Machine learning techniques work best when the data used for training re...
research
10/18/2019

OpenDenoising: an Extensible Benchmark for Building Comparative Studies of Image Denoisers

Image denoising has recently taken a leap forward due to machine learnin...
research
05/20/2022

Reliability-based Mesh-to-Grid Image Reconstruction

This paper presents a novel method for the reconstruction of images from...

Please sign up or login with your details

Forgot password? Click here to reset