Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding

TL;DR

This paper benchmarks the calibration and uncertainty estimation of 3D scene understanding models, revealing their shortcomings and proposing a new depth-aware scaling method to improve model reliability in safety-critical applications.

Contribution

It provides a comprehensive evaluation of 28 models across diverse datasets, analyzes factors affecting calibration, and introduces DeptS, a novel method for enhancing 3D model calibration.

Findings

Existing models often lack reliable uncertainty estimates.

Network capacity and data augmentation significantly impact calibration.

DeptS improves model calibration across various configurations.

Abstract

Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering effort to benchmark and scrutinize the reliability of 3D scene understanding models from an uncertainty estimation viewpoint. We comprehensively evaluate 28 state-of-the-art models across 10 diverse 3D datasets, uncovering insightful phenomena that cope with both the aleatoric and epistemic uncertainties in 3D scene understanding. We discover that despite achieving impressive levels of accuracy, existing models frequently fail to provide reliable uncertainty estimates -- a pitfall that critically undermines their applicability in safety-sensitive contexts. Through extensive analysis of key factors such as network capacity, LiDAR representations, rasterization resolutions, and 3D data augmentation techniques, we correlate these aspects directly with the model calibration efficacy. Furthermore, we introduce DeptS, a novel depth-aware scaling approach aimed at enhancing 3D model calibration. Extensive experiments across a wide range of configurations validate the superiority of our method. We hope this work could serve as a cornerstone for fostering reliable 3D scene understanding. Code and benchmark toolkit are publicly available.