Latent-Space Laplacian Pyramids for Adversarial Representation Learning with 3D Point Clouds
This work addresses a fundamental task in computer vision for applications in geometry processing, engineering, and design, but it appears incremental as it combines existing architectures.
The paper tackled the problem of generating finely detailed 3D surfaces, such as high-resolution point clouds, by proposing a hierarchical generative model using latent-space Laplacian pyramids, and it demonstrated that the model outperforms existing generative models for 3D point clouds.
Constructing high-quality generative models for 3D shapes is a fundamental task in computer vision with diverse applications in geometry processing, engineering, and design. Despite the recent progress in deep generative modelling, synthesis of finely detailed 3D surfaces, such as high-resolution point clouds, from scratch has not been achieved with existing approaches. In this work, we propose to employ the latent-space Laplacian pyramid representation within a hierarchical generative model for 3D point clouds. We combine the recently proposed latent-space GAN and Laplacian GAN architectures to form a multi-scale model capable of generating 3D point clouds at increasing levels of detail. Our evaluation demonstrates that our model outperforms the existing generative models for 3D point clouds.