Learning High Dynamic Range from Outdoor Panoramas
Authors:
- Jinsong ZhangJZJinsong Zhang
- Jean-Francois LalondeJLJean-Francois Lalonde
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4529-4538
Abstract
Outdoor lighting has extremely high dynamic range. This makes the process of capturing outdoor environment maps notoriously challenging since special equipment must be used. In this work, we propose an alternative approach. We first capture lighting with a regular, LDR omnidirectional camera, and aim to recover the HDR after the fact via a novel, learning-based inverse tonemapping method. We propose a deep autoencoder framework which regresses linear, high dynamic range data from non-linear, saturated, low dynamic range panoramas. We validate our method through a wide set of experiments on synthetic data, as well as on a novel dataset of real photographs with ground truth. Our approach finds applications in a variety of settings, ranging from outdoor light capture to image matching.Keywords
All Related Versions
This publication has 26 references indexed in Scilit:
- A reconfigurable camera add-on for high dynamic range, multispectral, polarization, and light-field imagingACM Transactions on Graphics, 2013
- An analytic model for full spectral sky-dome radianceACM Transactions on Graphics, 2012
- Estimating the Natural Illumination Conditions from a Single Outdoor ImageInternational Journal of Computer Vision, 2011
- Ldr2HdrACM Transactions on Graphics, 2007
- Do HDR displays support LDR content?ACM Transactions on Graphics, 2007
- A framework for inverse tone mappingThe Visual Computer, 2007
- Tone mapping for high dynamic range displays2007
- Direct HDR capture of the sun and sky2004
- Photographic tone reproduction for digital imagesACM Transactions on Graphics, 2002
- Rendering synthetic objects into real scenes1998