Fully in tensor computation manner: one‐shot dense 3D structured light and beyond. Issue 4 (3rd December 2020)

• Record Type: Journal Article
• Authors: Chen, Xuan‐Li; Van Gool, Luc
• Is Part Of: Cognitive computation and systems. Volume 2:Issue 4(2020)
• Page Start: 262
• Page End: 272
• Publication Date: 2020-12-03
• Subjects: image matching -- image reconstruction -- tensors; renowned correspondence search algorithm -- tensor‐SGM -- fully tensorised 3D reconstruction system -- multistructured light systems -- fully tensorised 3D structured light framework -- one‐shot dense 3D structured light -- low‐level parallelism -- application development -- simple manoeuvre tensor shift -- tensor computation -- PyTorch -- semiglobal matching -- off‐the‐shelf hardware; Cognitive science -- Periodicals; Artificial intelligence -- Periodicals; Neurosciences -- Periodicals; Computer science -- Periodicals; Neurosciences; Computer science; Cognitive science; Artificial intelligence; Periodicals; Electronic journals; 006.3
• DOI: 10.1049/ccs.2019.0027
• Languages: English
• ISSNs: 2517-7567

Abstract

Abstract : Tensor computation evolves fast towards a prosperous existence in recent years, e.g. PyTorch. An immediate advantage of using tensor computation is that one does not need to implement low‐level parallelism to attain efficient computation, which is of simplicity for both research and application development. The authors began with discovering that a simple manoeuvre 'tensor shift' could perform neighbourhood manipulation in very efficient parallel manner. Based on 'tensor shift', they derive the tensor version of a renowned correspondence search algorithm: semi‐global matching (SGM), which they prefix the name as tensor‐SGM. To evaluate their idea, they build‐up a novel and practical one‐shot structured light 3D acquisition system, which yields state‐of‐art reconstruction results using off‐the‐shelf hardware. This is the first fully tensorised 3D reconstruction system published to the authors' best knowledge, and it opens new possibilities. A major one is, in the same tensorised framework, they solved the pattern interfering problem which hinders multi‐structured light systems from working together. This part is marked as 'beyond' in this study to avoid confusing the readers the spotlight: the fully tensorised 3D structured light framework.