ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents

TL;DR

ArtiLatent is a novel generative framework that synthesizes realistic, articulated 3D objects with detailed geometry and appearance by modeling part geometry, articulation, and appearance in a unified latent space, enabling diverse and plausible 3D object generation.

Contribution

The paper introduces a unified latent space for modeling geometry, articulation, and appearance, along with a diffusion model and articulation-aware decoding for realistic 3D object synthesis.

Findings

Outperforms existing methods in geometric consistency.

Achieves high appearance fidelity across articulation states.

Generates diverse, physically plausible 3D objects.

Abstract

We propose ArtiLatent, a generative framework that synthesizes human-made 3D objects with fine-grained geometry, accurate articulation, and realistic appearance. Our approach jointly models part geometry and articulation dynamics by embedding sparse voxel representations and associated articulation properties, including joint type, axis, origin, range, and part category, into a unified latent space via a variational autoencoder. A latent diffusion model is then trained over this space to enable diverse yet physically plausible sampling. To reconstruct photorealistic 3D shapes, we introduce an articulation-aware Gaussian decoder that accounts for articulation-dependent visibility changes (e.g., revealing the interior of a drawer when opened). By conditioning appearance decoding on articulation state, our method assigns plausible texture features to regions that are typically occluded in static poses, significantly improving visual realism across articulation configurations. Extensive experiments on furniture-like objects from PartNet-Mobility and ACD datasets demonstrate that ArtiLatent outperforms existing approaches in geometric consistency and appearance fidelity. Our framework provides a scalable solution for articulated 3D object synthesis and manipulation.