Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches
Loading...
Date
2016
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We present a novel algorithm to reconstruct high-quality images from sampled pixels and gradients in gradient-domain rendering. Our approach extends screened Poisson reconstruction by adding additional regularization constraints. Our key idea is to exploit local patches in feature images, which contain per-pixels normals, textures, position, etc., to formulate these constraints. We describe a GPU implementation of our approach that runs on the order of seconds on megapixel images. We demonstrate a significant improvement in image quality over screened Poisson reconstruction under the L1 norm. Because we adapt the regularization constraints to the noise level in the input, our algorithm is consistent and converges to the ground truth.
Description
@article{10.1111:cgf.12829,
journal = {Computer Graphics Forum},
title = {{Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches}},
author = {Manzi, Marco and Vicini, Delio and Zwicker, Matthias},
year = {2016},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.12829}
}