Multi-resolution deep learning pipeline for dense large scale point clouds

TL;DR

This paper presents a multi-resolution deep learning pipeline that efficiently processes large-scale dense 3D point clouds by leveraging different resolutions for different object classes, balancing detail and computational cost.

Contribution

It introduces a novel multi-resolution deep learning pipeline that selectively exploits full resolution details for specific object classes in large-scale point clouds.

Findings

Improves detection accuracy for small objects using high-resolution data.

Reduces computational and memory costs by subsampling less critical areas.

Effectively balances detail preservation and efficiency in large-scale scene analysis.

Abstract

Recent development of 3D sensors allows the acquisition of extremely dense 3D point clouds of large-scale scenes. The main challenge of processing such large point clouds remains in the size of the data, which induce expensive computational and memory cost. In this context, the full resolution cloud is particularly hard to process, and details it brings are rarely exploited. Although fine-grained details are important for detection of small objects, they can alter the local geometry of large structural parts and mislead deep learning networks. In this paper, we introduce a new generic deep learning pipeline to exploit the full precision of large scale point clouds, but only for objects that require details. The core idea of our approach is to split up the process into multiple sub-networks which operate on different resolutions and with each their specific classes to retrieve. Thus, the pipeline allows each class to benefit either from noise and memory cost reduction of a sub-sampling or from fine-grained details.