FG-Net: Fast Large-Scale LiDAR Point Clouds Understanding Network Leveraging Correlated Feature Mining and Geometric-Aware Modelling
This work addresses the problem of efficient and accurate large-scale LiDAR point cloud understanding for applications requiring real-time performance, such as autonomous driving.
This paper introduces FG-Net, a deep learning framework for large-scale LiDAR point cloud understanding that avoids voxelization. It achieves accurate and real-time performance on a single NVIDIA GTX 1080 GPU, outperforming state-of-the-art methods in both accuracy and efficiency on real-world datasets.
This work presents FG-Net, a general deep learning framework for large-scale point clouds understanding without voxelizations, which achieves accurate and real-time performance with a single NVIDIA GTX 1080 GPU. First, a novel noise and outlier filtering method is designed to facilitate subsequent high-level tasks. For effective understanding purpose, we propose a deep convolutional neural network leveraging correlated feature mining and deformable convolution based geometric-aware modelling, in which the local feature relationships and geometric patterns can be fully exploited. For the efficiency issue, we put forward an inverse density sampling operation and a feature pyramid based residual learning strategy to save the computational cost and memory consumption respectively. Extensive experiments on real-world challenging datasets demonstrated that our approaches outperform state-of-the-art approaches in terms of accuracy and efficiency. Moreover, weakly supervised transfer learning is also conducted to demonstrate the generalization capacity of our method.