Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation

TL;DR

This paper introduces Hierarchical-Chain-of-Generation, an automated method that improves text-to-3D generation of complex objects by decomposing descriptions and hierarchically generating object parts with attribute accuracy.

Contribution

It proposes a novel hierarchical generation framework using large language models and Gaussian kernels to better handle complex attributes and occlusions in text-to-3D synthesis.

Findings

Produces structurally coherent 3D objects with complex attributes

Improves attribute binding accuracy in generated 3D models

Handles occlusions effectively through hierarchical part generation

Abstract

Recent text-to-3D models can render high-quality assets, yet they still stumble on objects with complex attributes. The key obstacles are: (1) existing text-to-3D approaches typically lift text-to-image models to extract semantics via text encoders, while the text encoder exhibits limited comprehension ability for long descriptions, leading to deviated cross-attention focus, subsequently wrong attribute binding in generated results. (2) Occluded object parts demand a disciplined generation order and explicit part disentanglement. Though some works introduce manual efforts to alleviate the above issues, their quality is unstable and highly reliant on manual information. To tackle above problems, we propose a automated method Hierarchical-Chain-of-Generation (HCoG). It leverages a large language model to decompose the long description into blocks representing different object parts, and orders them from inside out according to occlusions, forming a hierarchical chain. Within each block we first coarsely create components, then precisely bind attributes via target-region localization and corresponding 3D Gaussian kernel optimization. Between blocks, we introduce Gaussian Extension and Label Elimination to seamlessly generate new parts by extending new Gaussian kernels, re-assigning semantic labels, and eliminating unnecessary kernels, ensuring that only relevant parts are added without disrupting previously optimized parts. Experiments confirm that HCoG yields structurally coherent, attribute-faithful 3D objects with complex attributes. The code is available at https://github.com/Wakals/GASCOL .