PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
This addresses a novel problem in 3D generative shape modeling for computer vision and graphics applications, though it appears incremental as it builds on existing GAN and part-based methods.
The paper tackles the problem of generating 3D point cloud shapes from symbolic part tree representations, proposing a conditional GAN model that disentangles structural and geometric factors, with experimental results showing perceptually plausible and diverse outputs.
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.