MergeOcc: Bridge the Domain Gap between Different LiDARs for Robust Occupancy Prediction
This work addresses a domain gap issue for autonomous vehicles by enabling seamless deployment across heterogeneous LiDAR platforms, though it appears incremental as it builds on existing datasets and methods.
The paper tackles the problem of performance degradation in LiDAR-based 3D occupancy prediction when models trained on one dataset are deployed on different LiDARs, by developing MergeOcc, a generalized model that leverages multiple datasets to bridge domain gaps, resulting in enhanced robustness and outperforming state-of-the-art multi-modality methods on datasets like OpenOccupancy-nuScenes and SemanticKITTI.
LiDAR-based 3D occupancy prediction evolved rapidly alongside the emergence of large datasets. Nevertheless, the potential of existing diverse datasets remains underutilized as they kick in individually. Models trained on a specific dataset often suffer considerable performance degradation when deployed to real-world scenarios or datasets involving disparate LiDARs. This paper aims to develop a generalized model called MergeOcc, to simultaneously handle different LiDARs by leveraging multiple datasets. The gaps among LiDAR datasets primarily manifest in geometric disparities and semantic inconsistencies. Thus, MergeOcc incorporates a novel model featuring a geometric realignment module and a semantic label mapping module to enable multiple datasets training (MDT). The effectiveness of MergeOcc is validated through experiments on two prominent datasets for autonomous vehicles: OpenOccupancy-nuScenes and SemanticKITTI. The results demonstrate its enhanced robustness and remarkable performance across both types of LiDARs, outperforming several SOTA multi-modality methods. Notably, despite using an identical model architecture and hyper-parameter set, MergeOcc can significantly surpass the baseline due to its exposure to more diverse data. MergeOcc is considered the first cross-dataset 3D occupancy prediction pipeline that effectively bridges the domain gap for seamless deployment across heterogeneous platforms.