PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
arXiv:2003.08624
Abstract
3D generative shape modeling is a fundamental research area in computer vision and interactive computer graphics, with many real-world applications. This paper investigates the novel problem of generating 3D shape point cloud geometry from a symbolic part tree representation. In order to learn such a conditional shape generation procedure in an end-to-end fashion, we propose a conditional GAN "part tree"-to-"point cloud" model (PT2PC) that disentangles the structural and geometric factors. The proposed model incorporates the part tree condition into the architecture design by passing messages top-down and bottom-up along the part tree hierarchy. Experimental results and user study demonstrate the strengths of our method in generating perceptually plausible and diverse 3D point clouds, given the part tree condition. We also propose a novel structural measure for evaluating if the generated shape point clouds satisfy the part tree conditions.
ECCV 2020
References in corpus (15)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Generative Adversarial Text to Image Synthesis
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Learning Representations and Generative Models for 3D Point Clouds
- Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
- Learning What and Where to Draw
- Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
- Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
- InstaGAN: Instance-aware Image-to-Image Translation
- Learning to Infer and Execute 3D Shape Programs
- Learning Hierarchical Semantic Image Manipulation through Structured Representations
- High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
- Text to 3D Scene Generation with Rich Lexical Grounding
- Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
- PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes