DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
This addresses a bottleneck in point cloud analysis for indoor scene segmentation, though it appears incremental as it builds on existing architectures with dynamic pooling.
The paper tackled the problem of static pooling constraints in point cloud semantic scene segmentation by proposing DAR-Net, a dynamic aggregation network that uses a self-adaptive pooling skeleton, resulting in advantages over state-of-the-art methods on indoor scene datasets.
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.