An Analysis and Implementation of the HDR+ Burst Denoising Method

Iain · July 25, 2021, 12:00am

I thought some of you might find this interesting

http://www.ipol.im/pub/art/2021/336/

Abstract

HDR+ is an image processing pipeline presented by Google in 2016. At its core lies a denoising algorithm that uses a burst of raw images to produce a single higher quality image. Since it is designed as a versatile solution for smartphone cameras, it does not necessarily aim for the maximization of standard denoising metrics, but rather for the production of natural, visually pleasing images. In this article, we specifically discuss and analyze the HDR+ burst denoising algorithm architecture and the impact of its various parameters. With this publication, we provide an open source Python implementation of the algorithm, along with an interactive demo.

afre · July 25, 2021, 2:28am

I love IPOL. If only every publication has accessible papers, code and online demos as they do. I remember coming across the patent and paper of Google’s HDR+, which is essentially a summary of what needs to be done in an image enhancement workflow.