Adversarial Generation of Continuous Implicit Shape Representations
This work addresses 3D shape generation for computer graphics and vision applications, offering an incremental improvement over existing voxel and point cloud methods.
The authors tackled the problem of generating 3D shapes by developing a generative adversarial architecture that uses signed distance representations, enabling fine-grained details with arbitrary point density during inference. They trained on ShapeNet and validated performance quantitatively and qualitatively, showing realistic shape generation.
This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations. While the deep generation of shapes has been mostly tackled by voxel and surface point cloud approaches, our generator learns to approximate the signed distance for any point in space given prior latent information. Although structurally similar to generative point cloud approaches, this formulation can be evaluated with arbitrary point density during inference, leading to fine-grained details in generated outputs. Furthermore, we study the effects of using either progressively growing voxel- or point-processing networks as discriminators, and propose a refinement scheme to strengthen the generator's capabilities in modeling the zero iso-surface decision boundary of shapes. We train our approach on the ShapeNet benchmark dataset and validate, both quantitatively and qualitatively, its performance in generating realistic 3D shapes.