Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving
원문 초록
LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key challenges: 1) difficulty with efficient deployment and real-time execution; and 2) drastic performance degradation under weak calibration between LiDAR and cameras. To address these challenges, we propose CPGNet-LCF, a new multi-modal fusion framework extending the LiDAR-only CPGNet. CPGNet-LCF solves the first challenge by inheriting the easy deployment and real-time capabilities of CPGNet. For the second challenge, we introduce a novel weak calibration knowledge distillation strategy during training to improve the robustness against the weak calibration. CPGNet-LCF achieves state-of-the-art performance on the nuScenes and SemanticKITTI benchmarks. Remarkably, it can be easily deployed to run in 20ms per frame on a single Tesla V100 GPU using TensorRT TF16 mode. Furthermore, we benchmark performance over four weak calibration levels, demonstrating the robustness of our proposed approach.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
HNOSeg-XS: Extremely Small Hartley Neural Operator for Efficient and Resolution-Robust 3D Image Segmentation
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations
NRSeg: Noise-Resilient Learning for BEV Semantic Segmentation via Driving World Models
Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation
Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.