Regularizing Image Reconstruction for Gradient-Domain Rendering with Feature Patches

• Published in: Computer graphics forum Vol. 35; no. 2; pp. 263 - 273
• Main Authors: Manzi, M., Vicini, D., Zwicker, M.
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01.05.2016
• Subjects: Algorithms; Analysis; Categories and Subject Descriptors (according to ACM CCS); Computer graphics; I.3.3 [Computer Graphics]: Picture/Image Generation-Display Algorithms; Image processing systems; Image reconstruction; Reconstruction; Regularization; Rendering; Studies; Surface layer; Texture
• ISSN: 0167-7055; 1467-8659
• DOI: 10.1111/cgf.12829

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.