Supersampling of Data from Structured-light Scanner with Deep Learning

arXiv:2311.07432v2 Announce Type: replace
Abstract: This paper focuses on increasing the resolution of depth maps obtained from 3D cameras using structured light technology. Two deep learning models FDSR and DKN are modified to work with high-resolution data, and data pre-processing techniques are implemented for stable training. The models are trained on our custom dataset of 1200 3D scans. The resulting high-resolution depth maps are evaluated using qualitative and quantitative metrics. The approach for depth map upsampling offers benefits such as …

abstract arxiv cameras cs.cv data deep learning light maps paper pre-processing processing technology training type work