Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction
This addresses uncertainty in 3D bounding box prediction for robotics applications, but it is incremental as it builds on existing methods with a focus on output distribution modeling.
The paper tackles the challenge of predicting 3D bounding boxes by improving uncertainty modeling using an autoregressive prediction head, achieving strong results on datasets like SUN-RGBD, Scannet, KITTI, and a new simulated dataset COB-3D.
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.