Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance

TL;DR

To the best knowledge, this is the first 3D point cloud generation framework that fully integrates and enforces both symmetry and part priors throughout the generative process.

Abstract

We introduce the Quartet of Diffusions, a structure-aware point cloud generation framework that explicitly models part composition and symmetry. Unlike prior methods that treat shape generation as a holistic process or only support part composition, our approach leverages four coordinated diffusion models to learn distributions of global shape latents, symmetries, semantic parts, and their spatial assembly. This structured pipeline ensures guaranteed symmetry, coherent part placement, and diverse, high-quality outputs. By disentangling the generative process into interpretable components, our method supports fine-grained control over shape attributes, enabling targeted manipulation of individual parts while preserving global consistency. A central global latent further reinforces structural coherence across assembled parts. Our experiments show that the Quartet achieves state-of-the-art performance. To our best knowledge, this is the first 3D point cloud generation framework that fully integrates and enforces both symmetry and part priors throughout the generative process.

Figures (5)

• Figure 1: Overview of the Quartet's architecture. Four diffusions are employed to learn the distributions of shape latents, symmetries, parts, and assemblers. By explicitly modeling different distributions, the Quartet provides an interpretable and controllable framework to generate high-quality, diverse 3D shapes with guaranteed symmetry. Beige blocks denote learnable modules; gray blocks indicate outputs directly generated from the models.
• Figure 2: Point cloud airplanes, cars, and chairs with identified symmetry groups and corresponding fundamental domains for each color-coded part. Ref denotes reflection; Rot($\alpha$) denotes rotation by angle $\alpha$. Our symmetry formulation allows greater flexibility by supporting symmetries composed of multiple transformations, such as two reflections (chair legs (e)) or a rotation followed by a reflection (car wheels). Circular symmetry is approximated via small-angle rotations (chair seat (f)).
• Figure 3: Point cloud generation. Samples from the Quartet are visually appealing, diverse, and exhibit strong structural consistency. The last three columns illustrate targeted manipulation.
• Figure 4: Full point cloud generation results. Samples from the Quartet are visually appealing, diverse, and exhibit strong structural and symmetry consistency.
• Figure 5: More targeted manipulation results. We vary the yellow-highlighted parts while holding the remaining structure fixed.