Litcius/Paper detail

FastPillars: A Deployment-Friendly Pillar-Based 3D Detector

Sifan Zhou, Xinyu Zhang, Xiangxiang Chu, Bo Zhang, Ziyu Zhao, Xiaobo Lu

2025IEEE Transactions on Circuits and Systems for Video Technology13 citationsDOI

Abstract

The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference, which puts a hard barrier for deployment, especially for on-device applications. In this paper, in order to tackle the challenge of efficient 3D object detection from an industry perspective, we devise a deployment-friendly pillar-based 3D detector, termed FastPillars. Specifically, aiming to compensate the geometric information loss of pillar encoding. First, we design a novel lightweight Max-and-Attention Pillar Encoding (MAPE) module specially for enhancing small objects. Second, we propose a simple yet effective backbone design for pillar-based 3D detection, enhancing pillar representations. We construct FastPillars based on these designs, achieving high performance and low latency without SPConv. Extensive experiments on two large-scale datasets demonstrate the effectiveness and efficiency of FastPillars for on-device 3D detection regarding both performance and speed. Specifically, FastPillars delivers real-time state-of-the-art accuracy on Waymo Open Dataset with 1.8 × speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based). Code will be opened soon in: https://github.com/StiphyJay/FastPillars.

Topics & Concepts

Computer sciencePillarDetectorObject detectionEncoding (memory)Software deploymentConstruct (python library)Latency (audio)Code (set theory)Computer engineeringArtificial intelligenceSolid modelingReal-time computingObject (grammar)Computer visionComputer hardwareSource codeSimple (philosophy)Algorithm designPerformance improvementKey (lock)Decoding methodsBinary codeIterative reconstructionImage resolutionLow latency (capital markets)Advanced Neural Network ApplicationsRobotics and Sensor-Based LocalizationVisual Attention and Saliency Detection
FastPillars: A Deployment-Friendly Pillar-Based 3D Detector | Litcius