PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions

2020/03/19 by Kaichun Mo, Mo, Kaichun, He Wang +6 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Computational Geometry (cs.CG) #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR) #cs.CG #cs.CV #cs.GR

paper · pdf · doi:10.48550/arxiv.2003.08624

ECCV 2020

openalex publication_date 2020/03/19 · arxiv created 2020/07/16 · arxiv updated 2020/07/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• The Earth Mover's Distance as a Metric for Image Retrieval
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• A scalable active framework for region annotation in 3D shape collections
• Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts
• Learning Hierarchical Semantic Image Manipulation through Structured Representations
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Cited by

• Generative 3D Part Assembly via Dynamic Graph Learning

Related

• Shape Generation using Spatially Partitioned Point Clouds
• StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer
• StarNet: Style-Aware 3D Point Cloud Generation
• Multiresolution Tree Networks for 3D Point Cloud Processing
• Patch-Wise Point Cloud Generation: A Divide-and-Conquer Approach