4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation
About
In this work, we present a new paradigm, called 4D-StOP, to tackle the task of 4D Panoptic LiDAR Segmentation. 4D-StOP first generates spatio-temporal proposals using voting-based center predictions, where each point in the 4D volume votes for a corresponding center. These tracklet proposals are further aggregated using learned geometric features. The tracklet aggregation method effectively generates a video-level 4D scene representation over the entire space-time volume. This is in contrast to existing end-to-end trainable state-of-the-art approaches which use spatio-temporal embeddings that are represented by Gaussian probability distributions. Our voting-based tracklet generation method followed by geometric feature-based aggregation generates significantly improved panoptic LiDAR segmentation quality when compared to modeling the entire 4D volume using Gaussian probability distributions. 4D-StOP achieves a new state-of-the-art when applied to the SemanticKITTI test dataset with a score of 63.9 LSTQ, which is a large (+7%) improvement compared to current best-performing end-to-end trainable methods. The code and pre-trained models are available at: https://github.com/LarsKreuzberg/4D-StOP.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 4D Panoptic Segmentation | SemanticKITTI (val) | LSTQ67 | 35 | |
| 4D Panoptic Segmentation | SemanticKITTI (test) | LSTQ63.9 | 27 | |
| 4D Panoptic LiDAR Segmentation | SemanticKITTI (test) | LSTQ63.9 | 22 | |
| LiDAR Panoptic Segmentation | SemanticKITTI (val) | Scls60.3 | 22 | |
| 4D LiDAR Panoptic Segmentation | nuScenes panoptic (val) | Scls58.6 | 7 |