Small, Versatile and Mighty: A Range-View Perception Framework

TL;DR

This paper introduces a compact, efficient range-view perception framework for LiDAR data that achieves state-of-the-art 3D detection and seamlessly integrates multiple perception tasks using a pure convolutional architecture.

Contribution

It presents a novel multi-task framework with a range-view specific label assignment and view adaptive regression, significantly improving detection performance and multi-task capabilities.

Findings

Achieves new state-of-the-art detection performance on Waymo dataset.

Over 10 mAP improvement for vehicle detection compared to previous methods.

Successfully integrates semantic and panoptic segmentation without extra modules.

Abstract

Despite its compactness and information integrity, the range view representation of LiDAR data rarely occurs as the first choice for 3D perception tasks. In this work, we further push the envelop of the range-view representation with a novel multi-task framework, achieving unprecedented 3D detection performances. Our proposed Small, Versatile, and Mighty (SVM) network utilizes a pure convolutional architecture to fully unleash the efficiency and multi-tasking potentials of the range view representation. To boost detection performances, we first propose a range-view specific Perspective Centric Label Assignment (PCLA) strategy, and a novel View Adaptive Regression (VAR) module to further refine hard-to-predict box properties. In addition, our framework seamlessly integrates semantic segmentation and panoptic segmentation tasks for the LiDAR point cloud, without extra modules. Among range-view-based methods, our model achieves new state-of-the-art detection performances on the Waymo Open Dataset. Especially, over 10 mAP improvement over convolutional counterparts can be obtained on the vehicle class. Our presented results for other tasks further reveal the multi-task capabilities of the proposed small but mighty framework.