Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder

TL;DR

This paper introduces PillarHist, a height-aware histogram-based encoder that preserves height information and improves quantization in pillar-based 3D object detection, enhancing performance and efficiency.

Contribution

It proposes a novel height-aware pillar feature encoder using entropy-guided histograms to retain height information and facilitate quantization, improving existing pillar-based detectors.

Findings

Significantly improves detection accuracy.

Reduces computational overhead.

Enhances quantization friendliness.

Abstract

Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder, called PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar with the information entropy guidance. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance.