Learning Joint Intensity-Depth Sparse Representations

DOI10.1109/TIP.2014.2312645zbMATH Open1374.68427DBLPjournals/tip/TosicD14arXiv1201.0566WikidataQ50671121 ScholiaQ50671121MaRDI QIDQ4592200FDOQ4592200

Authors: I. Tošić, Sarah Drewes 

Publication date: 20 November 2017

Published in: IEEE Transactions on Image Processing (Search for Journal in Brave)

Abstract: This paper presents a method for learning overcomplete dictionaries composed of two modalities that describe a 3D scene: image intensity and scene depth. We propose a novel Joint Basis Pursuit (JBP) algorithm that finds related sparse features in two modalities using conic programming and integrate it into a two-step dictionary learning algorithm. JBP differs from related convex algorithms because it finds joint sparsity models with different atoms and different coefficient values for intensity and depth. This is crucial for recovering generative models where the same sparse underlying causes (3D features) give rise to different signals (intensity and depth). We give a theoretical bound for the sparse coefficient recovery error obtained by JBP, and show experimentally that JBP is far superior to the state of the art Group Lasso algorithm. When applied to the Middlebury depth-intensity database, our learning algorithm converges to a set of related features, such as pairs of depth and intensity edges or image textures and depth slants. Finally, we show that the learned dictionary and JBP achieve the state of the art depth inpainting performance on time-of-flight 3D data.

Full work available at URL: https://arxiv.org/abs/1201.0566

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Image analysis in multivariate analysis (62H35) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10) Machine vision and scene understanding (68T45)

This page was built for publication: Learning Joint Intensity-Depth Sparse Representations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4592200)