Out-of-Core Surface Reconstruction via Global $TGV$ Minimization

TL;DR

This paper introduces an out-of-core, GPU-accelerated surface reconstruction method using total generalized variation minimization, capable of processing large-scale, real-world depth data from various sources with noise filtering.

Contribution

The main novelty is an out-of-core OpenCL implementation of TGV minimization for large-scale surface reconstruction from depth maps.

Findings

Handles arbitrarily large scenes with scale diversity

Effective noise filtering due to TGV properties

GPU acceleration enables practical processing of big data

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.