Abstract-This paper presents a method for learning overcomplete dictionaries of atoms 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 we 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 bound for recovery error of sparse coefficients obtained by JBP, and show numerically that JBP is superior to the Group Lasso (GL) algorithm. When applied to the Middlebury depthintensity 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 JBP (with the learned dictionary) outperforms both GL and Total Variation (TV) on depth inpainting for timeof-flight 3D data.Index Terms-Sparse approximations, dictionary learning, hybrid image-depth sensors.
Variants in CAMK2-associated genes have recently been implicated in neurodevelopmental disorders and intellectual disability. The clinical manifestations reported in patients with mutations in these genes include intellectual disability (ranging from mild to severe), global developmental delay, seizures, delayed speech, behavioral abnormalities, hypotonia, episodic ataxia, progressive cerebellar atrophy, visual impairments, and gastrointestinal issues. Phenotypic heterogeneity has been postulated. We present a child with neurodevelopmental disorder caused by a pathogenic CAMK2B variant inherited from a healthy mother. A more mildly affected sib was determined to have the same variant. Monoallelic mutations in CAMK2B in patients have previously only been reported as de novo mutations. This report adds to the clinical phenotypic spectrum of the disease and demonstrates intrafamilial variability of expression of a CAMK2B mutation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.