OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

by   Xiaofeng Wang, et al.

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  2x 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 OpenOccupancy benchmark will boost the development of surrounding occupancy perception algorithms.


page 1

page 3

page 4

page 5

page 7


Boosting LiDAR-based Semantic Labeling by Cross-Modal Training Data Generation

Mobile robots and autonomous vehicles rely on multi-modal sensor setups ...

Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking

Panoptic scene understanding and tracking of dynamic agents are essentia...

Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection

There are two critical sensors for 3D perception in autonomous driving, ...

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

This paper introduces VolMap, a real-time approach for the semantic segm...

SURE-Val: Safe Urban Relevance Extension and Validation

To evaluate perception components of an automated driving system, it is ...

PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation

The requirement of fine-grained perception by autonomous driving systems...

MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models

Despite tremendous advancements in bird's-eye view (BEV) perception, exi...

Code Repositories


OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perception

view repo

Please sign up or login with your details

Forgot password? Click here to reset