OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception
Authors:
Top Cited Papers
- 1 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 17804-17813
Abstract
Semantic occupancy perception is essential for autonomous driving, as automated vehicles require a fine-grained perception of the 3D urban structures. However, existing relevant benchmarks lack diversity in urban scenes, and they only evaluate front-view predictions. Towards a comprehensive benchmarking of surrounding perception algorithms, we propose OpenOccupancy, which is the first surrounding semantic occupancy perception benchmark. In the OpenOccupancy benchmark, we extend the large-scale nuScenes dataset with dense semantic occupancy annotations. Previous annotations rely on LiDAR points superimposition, where some occupancy labels are missed due to sparse LiDAR channels. To mitigate the problem, we introduce the Augmenting And Purifying (AAP) pipeline to ~ 2× densify the annotations, where ∼4000 human hours are involved in the labeling process. Besides, camera-based, LiDAR-based and multi-modal baselines are established for the OpenOccupancy benchmark. Furthermore, considering the complexity of surrounding occupancy perception lies in the computational burden of high-resolution 3D predictions, we propose the Cascade Occupancy Network (CONet) to refine the coarse prediction, which relatively enhances the performance by ∼30% than the baseline. We hope the OpenOccupancy benchmark ‡ will boost the development of surrounding occupancy perception algorithms.Keywords
This publication has 40 references indexed in Scilit:
- 3D Semantic Scene Completion: A SurveyInternational Journal of Computer Vision, 2022
- SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion2020
- LMSCNet: Lightweight Multiscale 3D Semantic Completion2020
- Efficient Semantic Scene Completion Network with Spatial Group Convolution2018
- Feature Pyramid Networks for Object Detection2017
- SceneNN: A Scene Meshes Dataset with aNNotations2016
- Deep Residual Learning for Image Recognition2016
- Structured Prediction of Unobserved Voxels from a Single Depth Image2016
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Indoor Segmentation and Support Inference from RGBD Images2012