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

ICLR 2026 Conference Submission14559 Authors

Keywords: computer vision, point cloud generation, structure-aware, part-based, symmetry-aware

TL;DR: We propose a structure-aware point cloud generation pipeline through part and symmetry guidance, guaranteeing symmetry and achieving SOTA results

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.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 14559