PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks
This work addresses point cloud upsampling for computer vision applications, offering incremental improvements in efficiency and performance.
The paper tackles point cloud upsampling by proposing NodeShuffle, a GCN-based upsampling module, and Inception DenseGCN, a multi-scale feature extractor, combined into PU-GCN, which achieves state-of-the-art performance with fewer parameters and more efficient inference.
The effectiveness of learning-based point cloud upsampling pipelines heavily relies on the upsampling modules and feature extractors used therein. For the point upsampling module, we propose a novel model called NodeShuffle, which uses a Graph Convolutional Network (GCN) to better encode local point information from point neighborhoods. NodeShuffle is versatile and can be incorporated into any point cloud upsampling pipeline. Extensive experiments show how NodeShuffle consistently improves state-of-the-art upsampling methods. For feature extraction, we also propose a new multi-scale point feature extractor, called Inception DenseGCN. By aggregating features at multiple scales, this feature extractor enables further performance gain in the final upsampled point clouds. We combine Inception DenseGCN with NodeShuffle into a new point upsampling pipeline called PU-GCN. PU-GCN sets new state-of-art performance with much fewer parameters and more efficient inference.