Learning High Dynamic Range from Outdoor Panoramas
release_zlqzkrlc3ja2dlpvt245liddza
by
Jinsong Zhang, Jean-François Lalonde
2017
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.
In text/plain
format
Archived Files and Locations
application/pdf 7.4 MB
file_lfoks3tcjffxfkctstgbztgj2u
|
arxiv.org (repository) web.archive.org (webarchive) |
1703.10200v4
access all versions, variants, and formats of this works (eg, pre-prints)