KAUST DepartmentVisual Computing Center, King Abdullah University of Science and Technology (KAUST)
Online Publication Date2017-12-25
Print Publication Date2017-10
Permanent link to this recordhttp://hdl.handle.net/10754/626836
MetadataShow full item record
AbstractConvolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high-dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaicing and 4D light field view synthesis.
SponsorsVCC KAUST Baseline Funding, Terman Faculty Fellowship, Intel Compressive Sensing Alliance, National Science Foundation (IIS 1553333), and NSF/Intel Partnership on Visual and Experiential Computing (IIS 1539120).
Conference/Event nameInternational Conference on Computer Vision (ICCV)