Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

TL;DR

This paper introduces an autoregressive approach to model uncertainty in 3D bounding box prediction, improving confidence estimation and addressing ambiguities in robotics applications, validated on multiple datasets including a new simulated one.

Contribution

It proposes an autoregressive prediction head for better uncertainty modeling in 3D bounding boxes and releases a new dataset to explore real-world ambiguities.

Findings

Achieves strong results on SUN-RGBD, Scannet, KITTI datasets.

Provides high-confidence predictions with meaningful uncertainty measures.

Highlights new ambiguity types in robotics scenarios.

Abstract

3D bounding boxes are a widespread intermediate representation in many computer vision applications. However, predicting them is a challenging task, largely due to partial observability, which motivates the need for a strong sense of uncertainty. While many recent methods have explored better architectures for consuming sparse and unstructured point cloud data, we hypothesize that there is room for improvement in the modeling of the output distribution and explore how this can be achieved using an autoregressive prediction head. Additionally, we release a simulated dataset, COB-3D, which highlights new types of ambiguity that arise in real-world robotics applications, where 3D bounding box prediction has largely been underexplored. We propose methods for leveraging our autoregressive model to make high confidence predictions and meaningful uncertainty measures, achieving strong results on SUN-RGBD, Scannet, KITTI, and our new dataset.