TEOcc: Radar-camera Multi-modal Occupancy Prediction via Temporal Enhancement

TL;DR

TEOcc introduces a multi-modal, temporal enhancement approach for 3D occupancy prediction in autonomous driving, leveraging long-term temporal information and multi-modal data to improve accuracy while reducing computational costs.

Contribution

The paper proposes a novel temporal enhancement branch for occupancy prediction that improves accuracy and can be integrated into existing methods, with a focus on multi-modal data and efficiency.

Findings

Achieves state-of-the-art results on nuScenes benchmark.

Temporal enhancement improves occupancy prediction accuracy.

Module is lightweight and easily integrable into existing systems.

Abstract

As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view or neural radiance fields, while ignoring the advantages of using long-temporal information. In this paper, we propose a radar-camera multi-modal temporal enhanced occupancy prediction network, dubbed TEOcc. Our method is inspired by the success of utilizing temporal information in 3D object detection. Specifically, we introduce a temporal enhancement branch to learn temporal occupancy prediction. In this branch, we randomly discard the t-k input frame of the multi-view camera and predict its 3D occupancy by long-term and short-term temporal decoders separately with the information from other adjacent frames and multi-modal inputs. Besides, to reduce computational costs and incorporate multi-modal inputs, we specially designed 3D convolutional layers for long-term and short-term temporal decoders. Furthermore, since the lightweight occupancy prediction head is a dense classification head, we propose to use a shared occupancy prediction head for the temporal enhancement and main branches. It is worth noting that the temporal enhancement branch is only performed during training and is discarded during inference. Experiment results demonstrate that TEOcc achieves state-of-the-art occupancy prediction on nuScenes benchmarks. In addition, the proposed temporal enhancement branch is a plug-and-play module that can be easily integrated into existing occupancy prediction methods to improve the performance of occupancy prediction. The code and models will be released at https://github.com/VDIGPKU/TEOcc.