HDR Image Noise Estimation for Denoising Tone Mapped Images
We propose a method for denoising images created by any tone mapping operator.
November 24, 2015
Conference for Visual Media Production (CVMP) 2015
Authors
Miguel Granados (Disney Research/MPI for Informatics)
Tunc Aydin (Disney Research)
J. Rafael Tena (Disney Research)
Jean-François Lalonde (Laval University)
Christian Theobalt (MPI for Informatics)
HDR Image Noise Estimation for Denoising Tone Mapped Images
Tone mapping operators are designed to compress the dynamic range of high dynamic range (HDR) images while preserving the perceived image brightness, but they often enhance image noise in the process, specially in low- light conditions. We propose a method for denoising images created by any tone mapping operator. Our approach leverages the noise distribution of the HDR image to guide the range kernel of a cross-bilateral filter that is used to denoise the tone mapped image. When the noise distribution is unknown, we use a new method to automatically estimate it assuming that the HDR image was produced as an average of multiple exposures taken in RAW or JPEG compressed format. Our method performs quantitatively better than existing denoising methods applied on either the original HDR or the tone-mapped images directly, and a user study confirms that it produces visually preferable results.
