Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches

Manzi, Marco; Vicini, Delio Aleardo; Zwicker, Matthias (2016). Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches. Computer graphics forum, 35(2), pp. 263-273. Blackwell 10.1111/cgf.12829

[img] Text
FeaturePatchesForGPTReconstruction.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (9MB) | Request a copy

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.

Item Type:

Journal Article (Original Article)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF) > Computer Graphics Group (CGG)
08 Faculty of Science > Institute of Computer Science (INF)

UniBE Contributor:

Manzi, Marco; Vicini, Delio Aleardo and Zwicker, Matthias

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics

ISSN:

0167-7055

Publisher:

Blackwell

Funders:

[4] Swiss National Science Foundation

Projects:

[UNSPECIFIED] Efficient Sampling and Reconstruction for Image Synthesis 143886

Language:

English

Submitter:

Matthias Zwicker

Date Deposited:

08 Jun 2016 16:33

Last Modified:

08 Jun 2016 16:33

Publisher DOI:

10.1111/cgf.12829

BORIS DOI:

10.7892/boris.81157

URI:

https://boris.unibe.ch/id/eprint/81157

Actions (login required)

Edit item Edit item
Provide Feedback