OccCylindrical: Multi-Modal Fusion with Cylindrical Representation for 3D Semantic Occupancy Prediction
This addresses the problem of fine-grained detail loss in sensor fusion for autonomous vehicle perception, though it is incremental as it builds on existing multi-modal fusion approaches.
The paper tackled 3D semantic occupancy prediction for autonomous vehicles by proposing OccCylindrical, a multi-modal fusion method using cylindrical coordinates, which achieved state-of-the-art performance on the nuScenes dataset, including in challenging rainy and nighttime scenarios.
The safe operation of autonomous vehicles (AVs) is highly dependent on their understanding of the surroundings. For this, the task of 3D semantic occupancy prediction divides the space around the sensors into voxels, and labels each voxel with both occupancy and semantic information. Recent perception models have used multisensor fusion to perform this task. However, existing multisensor fusion-based approaches focus mainly on using sensor information in the Cartesian coordinate system. This ignores the distribution of the sensor readings, leading to a loss of fine-grained details and performance degradation. In this paper, we propose OccCylindrical that merges and refines the different modality features under cylindrical coordinates. Our method preserves more fine-grained geometry detail that leads to better performance. Extensive experiments conducted on the nuScenes dataset, including challenging rainy and nighttime scenarios, confirm our approach's effectiveness and state-of-the-art performance. The code will be available at: https://github.com/DanielMing123/OccCylindrical