Out-of-Core Surface Reconstruction via Global TGV Minimization

2021/07/30 by Poliarnyi, Nikolai
#C.2.4 #Computer Vision and Pattern Recognition (cs.CV) #Distributed #FOS: Computer and information sciences #Graphics (cs.GR) #I.3.5 #I.4.8 #Parallel #and Cluster Computing (cs.DC)

paper · doi:10.48550/arxiv.2107.14790

Abstract

We present an out-of-core variational approach for surface reconstruction from a set of aligned depth maps. Input depth maps are supposed to be reconstructed from regular photos or/and can be a representation of terrestrial LIDAR point clouds. Our approach is based on surface reconstruction via total generalized variation minimization (TGV) because of its strong visibility-based noise-filtering properties and GPU-friendliness. Our main contribution is an out-of-core OpenCL-accelerated adaptation of this numerical algorithm which can handle arbitrarily large real-world scenes with scale diversity.

Related

• Fast Algorithms for Surface Reconstruction from Point Cloud
• Locally controlled globally smooth ground surface reconstruction from terrestrial point clouds
• Image-Guided Depth Upsampling via Hessian and TV Priors
• HessianForge: Scalable LiDAR reconstruction with Physics-Informed Neural Representation and Smoothness Energy Constraints
• Accurate and Efficient Surface Reconstruction from Point Clouds via Geometry-Aware Local Adaptation