Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive scene Segmentation
This addresses the cost barrier for deploying high-resolution LiDAR in autonomous driving by enabling effective segmentation with low-cost sensors, though it is incremental as it builds on existing super-resolution and segmentation methods.
The paper tackles the problem of sparse LiDAR data from low-cost sensors degrading 3D semantic segmentation accuracy in autonomous driving by introducing an end-to-end framework that jointly optimizes LiDAR super-resolution and segmentation, achieving performance comparable to models using high-resolution 64-channel LiDAR data.
High-resolution LiDAR data plays a critical role in 3D semantic segmentation for autonomous driving, but the high cost of advanced sensors limits large-scale deployment. In contrast, low-cost sensors such as 16-channel LiDAR produce sparse point clouds that degrade segmentation accuracy. To overcome this, we introduce the first end-to-end framework that jointly addresses LiDAR super-resolution (SR) and semantic segmentation. The framework employs joint optimization during training, allowing the SR module to incorporate semantic cues and preserve fine details, particularly for smaller object classes. A new SR loss function further directs the network to focus on regions of interest. The proposed lightweight, model-based SR architecture uses significantly fewer parameters than existing LiDAR SR approaches, while remaining easily compatible with segmentation networks. Experiments show that our method achieves segmentation performance comparable to models operating on high-resolution and costly 64-channel LiDAR data.