Beyond Spatial Compression: Interface-Centric Generative States for Open-World 3D Structure

TL;DR

This paper introduces interface-centric generative states for 3D models, enabling explicit control and repair of component relationships during decoding, improving robustness in open-world assets.

Contribution

It proposes a novel tokenization approach, C2LT-3D, that exposes local geometry and attachment variables for better structural reasoning and repair.

Findings

C2LT-3D improves structural robustness in open-world 3D assets.

Latent variables remain actionable under adversarial attachment settings.

Supports attachment validation and structural repair during decoding.

Abstract

Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership and attachment validity implicit. In open-world assets with intersecting components, noisy topology, and weak canonical structure, this creates a representation mismatch: local shape, component identity, and assembly relations become entangled in a latent stream and are not natively addressable during decoding. We formulate an alternative view, interface-centric generative states, in which tokenization constructs an operational state rather than a passive compressed code. The state exposes local geometry, component ownership, and attachment validity as variables that can be queried, constrained, and repaired during decoding. We instantiate this formulation with Component-Conditioned Canonical Local Tokens (C2LT-3D), factorizing representation into canonical local geometry, partition-conditioned context, and relational seam variables. Each factor targets a distinct failure mode of compression-centric tokens: pose leakage, cross-component interference, or invalid local attachment. This exposed state supports attachment validation, latent structural repair, targeted intervention, and constrained serialization without a separate post-hoc structure recovery module. Trained on single-object CAD models and evaluated zero-shot on open-world multi-component assets, C2LT-3D improves structural robustness and shows that its latent variables remain actionable under adversarial attachment settings. These results suggest that open-world 3D generative representations should be evaluated not only by reconstruction fidelity, but by whether their discrete states remain operational for assembly-level structural reasoning.