Building-PCC: Building Point Cloud Completion Benchmarks

TL;DR

This paper introduces Building-PCC, a new benchmark dataset for evaluating deep learning methods on urban building point cloud completion, addressing challenges of data incompleteness in 3D urban scene modeling.

Contribution

It establishes a real-world benchmark dataset for building point cloud completion and provides a comprehensive evaluation of existing deep learning methods on this task.

Findings

Deep learning methods vary in performance on building point cloud completion.

Key challenges include handling occlusion and data incompleteness.

Benchmark promotes future research in 3D urban scene reconstruction.

Abstract

With the rapid advancement of 3D sensing technologies, obtaining 3D shape information of objects has become increasingly convenient. Lidar technology, with its capability to accurately capture the 3D information of objects at long distances, has been widely applied in the collection of 3D data in urban scenes. However, the collected point cloud data often exhibit incompleteness due to factors such as occlusion, signal absorption, and specular reflection. This paper explores the application of point cloud completion technologies in processing these incomplete data and establishes a new real-world benchmark Building-PCC dataset, to evaluate the performance of existing deep learning methods in the task of urban building point cloud completion. Through a comprehensive evaluation of different methods, we analyze the key challenges faced in building point cloud completion, aiming to promote innovation in the field of 3D geoinformation applications. Our source code is available at https://github.com/tudelft3d/Building-PCC-Building-Point-Cloud-Completion-Benchmarks.git.