LATTICE: Democratize High-Fidelity 3D Generation at Scale

TL;DR

LATTICE introduces a scalable framework for high-fidelity 3D asset generation by combining a novel semi-structured representation with a two-stage generation pipeline, bridging the quality gap between 2D and 3D models.

Contribution

The paper proposes VoxSet, a new compact 3D representation with explicit structure, and a two-stage generation process that improves scalability and quality of 3D asset synthesis.

Findings

Achieves state-of-the-art performance in 3D asset generation.

Supports arbitrary resolution decoding and flexible inference schemes.

Enables efficient training and high-quality 3D outputs.

Abstract

We present LATTICE, a new framework for high-fidelity 3D asset generation that bridges the quality and scalability gap between 3D and 2D generative models. While 2D image synthesis benefits from fixed spatial grids and well-established transformer architectures, 3D generation remains fundamentally more challenging due to the need to predict both spatial structure and detailed geometric surfaces from scratch. These challenges are exacerbated by the computational complexity of existing 3D representations and the lack of structured and scalable 3D asset encoding schemes. To address this, we propose VoxSet, a semi-structured representation that compresses 3D assets into a compact set of latent vectors anchored to a coarse voxel grid, enabling efficient and position-aware generation. VoxSet retains the simplicity and compression advantages of prior VecSet methods while introducing explicit structure into the latent space, allowing positional embeddings to guide generation and enabling strong token-level test-time scaling. Built upon this representation, LATTICE adopts a two-stage pipeline: first generating a sparse voxelized geometry anchor, then producing detailed geometry using a rectified flow transformer. Our method is simple at its core, but supports arbitrary resolution decoding, low-cost training, and flexible inference schemes, achieving state-of-the-art performance on various aspects, and offering a significant step toward scalable, high-quality 3D asset creation.