PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling
This work addresses point cloud upsampling for applications like 3D modeling and computer vision, offering incremental improvements in handling high-frequency details.
The authors tackled 3D point cloud upsampling by proposing a frequency-aware generative adversarial network (PUFA-GAN) that generates evenly distributed points with clean high-frequency regions, achieving better visual quality than state-of-the-art methods as demonstrated by objective and subjective results.
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions. The generator of our network includes a dynamic graph hierarchical residual aggregation unit and a hierarchical residual aggregation unit for point feature extraction and upsampling, respectively. The former extracts multiscale point-wise descriptive features, while the latter captures rich feature details with hierarchical residuals. To generate neat edges, our discriminator uses a graph filter to extract and retain high frequency points. The generated high resolution point cloud and corresponding high frequency points help the discriminator learn the global and high frequency properties of the point cloud. We also propose an identity distribution loss function to make sure that the upsampled points remain on the underlying surface of the input low resolution point cloud. To assess the regularity of the upsampled points in high frequency regions, we introduce two evaluation metrics. Objective and subjective results demonstrate that the visual quality of the upsampled point clouds generated by our method is better than that of the state-of-the-art methods.