Multiway K-Clustered Tensor Approximation: Toward

This article presents a generalized sparse multilinear model, namely multi-way K-clustered tensor approximation (MK-CTA), for synthesizing pho-torealistic 3D images from large-scale multidimensional visual datasets. MK-CTA extends previous tensor approximation algorithms, particularly K-clustered tensor approximation (K-CTA) [Tsai and Shih 2012], to parti-tion a multidimensional dataset along more than one dimension into over-lapped clusters. On the contrary, K-CTA only sparsely clusters a dataset along just one dimension and often fails to efficiently approximate other un-clustered dimensions. By generalizing K-CTA with multiway sparse clus-tering, MK-CTA can be regarded as a novel sparse tensor-based model that simultaneously exploits the intra- and inter-cluster coherence among dif-ferent dimensions of an input dataset. Our experiments demonstrate that MK-CTA can accurately and compactly represent various multidimensional datasets with complex and sharp visual features, including bidirectional tex-ture functions (BTFs) [Dana et al. 1999], time-varying light fields (TVLFs