WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation

TL;DR

WarpingGAN introduces a novel 3D point cloud generation method that warps multiple priors into shapes using a local-warping function, achieving high quality and efficiency with a single lightweight network.

Contribution

It proposes a unified local-warping mechanism for 3D shape generation from multiple priors, improving quality and efficiency over existing direct mapping methods.

Findings

Outperforms state-of-the-art in quantitative metrics

Produces high-quality visual 3D shapes

Generates uniformly distributed point clouds efficiently

Abstract

We propose WarpingGAN, an effective and efficient 3D point cloud generation network. Unlike existing methods that generate point clouds by directly learning the mapping functions between latent codes and 3D shapes, Warping-GAN learns a unified local-warping function to warp multiple identical pre-defined priors (i.e., sets of points uniformly distributed on regular 3D grids) into 3D shapes driven by local structure-aware semantics. In addition, we also ingeniously utilize the principle of the discriminator and tailor a stitching loss to eliminate the gaps between different partitions of a generated shape corresponding to different priors for boosting quality. Owing to the novel generating mechanism, WarpingGAN, a single lightweight network after one-time training, is capable of efficiently generating uniformly distributed 3D point clouds with various resolutions. Extensive experimental results demonstrate the superiority of our WarpingGAN over state-of-the-art methods in terms of quantitative metrics, visual quality, and efficiency. The source code is publicly available at https://github.com/yztang4/WarpingGAN.git.