1. AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation
- Author
-
Liong, Venice Erin, Nguyen, Thi Ngoc Tho, Widjaja, Sergi, Sharma, Dhananjai, and Chong, Zhuang Jie
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,Computer Science - Machine Learning ,Computer Science - Robotics - Abstract
In this paper, we present an Assertion-based Multi-View Fusion network (AMVNet) for LiDAR semantic segmentation which aggregates the semantic features of individual projection-based networks using late fusion. Given class scores from different projection-based networks, we perform assertion-guided point sampling on score disagreements and pass a set of point-level features for each sampled point to a simple point head which refines the predictions. This modular-and-hierarchical late fusion approach provides the flexibility of having two independent networks with a minor overhead from a light-weight network. Such approaches are desirable for robotic systems, e.g. autonomous vehicles, for which the computational and memory resources are often limited. Extensive experiments show that AMVNet achieves state-of-the-art results in both the SemanticKITTI and nuScenes benchmark datasets and that our approach outperforms the baseline method of combining the class scores of the projection-based networks., Comment: 10 pages, 7 figures, 5 tables
- Published
- 2020