DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
arXiv:1907.12022
Abstract
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. In this paper, we propose DAR-Net, a novel network architecture that focuses on dynamic feature aggregation. The central idea of DAR-Net is generating a self-adaptive pooling skeleton that considers both scene complexity and local geometry features. Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advantages of the proposed approach compared to state-of-the-art architectures that adopt static pooling methods.
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Learning shape correspondence with anisotropic convolutional neural networks
- SO-Net: Self-Organizing Network for Point Cloud Analysis
- OctNet: Learning Deep 3D Representations at High Resolutions
- FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
- MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds
- PointWise: An Unsupervised Point-wise Feature Learning Network