2020/12/17 by Kangcheng Liu, Zhi Gao, Liu, Kangcheng +5
Computer Science · Earth and Planetary Sciences · Engineering · Environmental Science · #3D Shape Modeling and Analysis #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Remote Sensing and LiDAR Applications #Robotics (cs.RO) #cs.CV #cs.RO
paper · pdf · doi:10.48550/arxiv.2012.09439
openalex publication_date 2020/12/17 · openalex created_date 2020/12/21 · arxiv created 2021/06/17 · arxiv updated 2021/06/18 · openalex updated_date 2026/07/28
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.