De-lighting a High-resolution Picture for Material Acquisition

Loading...
Thumbnail Image
Date
2019
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We propose a deep-learning based method for the removal of shades, projected shadows and highlights from a single picture of a quasi-planar surface captured in natural lighting conditions with any kind of camera device. To achieve this, we train an encoder-decoder to process physically based materials, rendered under various lighting conditions, to infer its spatially-varying albedo. Our network processes relatively small image tiles (512x512 pixels) and we propose a solution to handle larger image resolutions by solving a Poisson system across these tiles.
Description

        
@inproceedings{
10.2312:sr.20191222
, booktitle = {
Eurographics Symposium on Rendering - DL-only and Industry Track
}, editor = {
Boubekeur, Tamy and Sen, Pradeep
}, title = {{
De-lighting a High-resolution Picture for Material Acquisition
}}, author = {
Martin, Rosalie
and
Meyer, Arthur
and
Pesare, Davide
}, year = {
2019
}, publisher = {
The Eurographics Association
}, ISSN = {
1727-3463
}, ISBN = {
978-3-03868-095-6
}, DOI = {
10.2312/sr.20191222
} }
Citation