HALS: A Height-Aware Lidar Super-Resolution Framework for Autonomous Driving

TL;DR

This paper introduces HALS, a novel height-aware lidar super-resolution framework that improves pointcloud upsampling for autonomous driving, achieving state-of-the-art results by leveraging height distribution and specialized architecture.

Contribution

The paper provides a comprehensive benchmark of existing lidar upsampling methods and proposes HALS, a new model with multiple upsampling branches and a surface-normal loss, enhancing super-resolution performance.

Findings

HALS outperforms existing methods on multiple datasets.

Benchmarking reveals strengths and weaknesses of current approaches.

Height-aware design improves lidar upsampling accuracy.

Abstract

Lidar sensors are costly yet critical for understanding the 3D environment in autonomous driving. High-resolution sensors provide more details about the surroundings because they contain more vertical beams, but they come at a much higher cost, limiting their inclusion in autonomous vehicles. Upsampling lidar pointclouds is a promising approach to gain the benefits of high resolution while maintaining an affordable cost. Although there exist many pointcloud upsampling frameworks, a consistent comparison of these works against each other on the same dataset using unified metrics is still missing. In the first part of this paper, we propose to benchmark existing methods on the Kitti dataset. In the second part, we introduce a novel lidar upsampling model, HALS: Height-Aware Lidar Super-resolution. HALS exploits the observation that lidar scans exhibit a height-aware range distribution and adopts a generator architecture with multiple upsampling branches of different receptive fields. HALS regresses polar coordinates instead of spherical coordinates and uses a surface-normal loss. Extensive experiments show that HALS achieves state-of-the-art performance on 3 real-world lidar datasets.