PU-GAN: a Point Cloud Upsampling Adversarial Network
This addresses the need for high-quality point cloud upsampling in 3D scanning and reconstruction, but it is incremental as it builds on existing GAN-based methods with specific improvements.
The paper tackles the problem of sparse, noisy, and non-uniform point clouds from range scans by proposing PU-GAN, a point cloud upsampling adversarial network, which achieves state-of-the-art results in distribution uniformity, proximity-to-surface, and 3D reconstruction quality.
Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.