LiteViLNet: Lightweight Vision-LiDAR Fusion Network for Efficient Road Segmentation

Road segmentation is a fundamental perception task for autonomous driving and mobile robotics, where both appearance and geometric cues must be processed under edge-computing constraints. Existing multi-modal approaches often improve accuracy with large encoders or expensive global interaction, which limits their use on embedded platforms. We present LiteViLNet, a lightweight RGB-geometry fusion network that combines a MobileNetV3 RGB encoder with a 0.12M-parameter depth-wise-separable geometry encoder. A multi-scale feature fusion module performs modality-specific enhancement, global-query cross-modal interaction, and adaptive gating, while a depth-wise large-kernel bridge enlarges the contextual support of the deepest representation with low overhead. The resulting U-Net-style decoder uses deep supervision only during training. On the KITTI Road benchmark, the 14.04M-parameter full model obtains 97.23±0.15% MaxF. On the held-out ORFD test set under the released OFF-Net evaluation protocol, the full model achieves 96.74±0.09% F-score and 93.68±0.18% IoU. On a Jetson Orin NX, model-only PyTorch FP16 inference reaches 22.18±0.21 FPS; a separate TensorRT FP16 measurement reaches 68.73±0.06 FPS on the Jetson. Camera-depth adaptations and perception-and-control demonstrations on three heterogeneous robot platforms further illustrate the portability of the dual-stream design.