MFSeg: Efficient Multi-frame 3D Semantic Segmentation
This work addresses efficient multi-frame 3D semantic segmentation for autonomous driving systems, representing an incremental improvement over prior methods.
The paper tackled the problem of 3D semantic segmentation from point cloud sequences by proposing MFSeg, which aggregates features across frames and uses a lightweight decoder to reduce computational overhead while achieving high accuracy, outperforming existing methods on nuScenes and Waymo datasets.
We propose MFSeg, an efficient multi-frame 3D semantic segmentation framework. By aggregating point cloud sequences at the feature level and regularizing the feature extraction and aggregation process, MFSeg reduces computational overhead while maintaining high accuracy. Moreover, by employing a lightweight MLP-based point decoder, our method eliminates the need to upsample redundant points from past frames. Experiments on the nuScenes and Waymo datasets show that MFSeg outperforms existing methods, demonstrating its effectiveness and efficiency.