CMDFusion: Bidirectional Fusion Network with Cross-modality Knowledge Distillation for LIDAR Semantic Segmentation

• Published in: arXiv.org
• Main Authors: Cen, Jun, Zhang, Shiwei, Pei, Yixuan, Li, Kun, Zheng, Hang, Luo, Maochun, Zhang, Yingya, Chen, Qifeng
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 09.07.2023
• Subjects: Cameras; Color imagery; Distillation; Image segmentation; Inference; Knowledge; Lidar; Semantic segmentation; Semantics; Three dimensional models

2D RGB images and 3D LIDAR point clouds provide complementary knowledge for the perception system of autonomous vehicles. Several 2D and 3D fusion methods have been explored for the LIDAR semantic segmentation task, but they suffer from different problems. 2D-to-3D fusion methods require strictly pa...