T2TD: Text-3D Generation Model based on Prior Knowledge Guidance

TL;DR

This paper introduces T2TD, a novel text-3D generation model that leverages prior knowledge, including a knowledge graph and causal inference, to improve 3D model quality from textual descriptions, outperforming state-of-the-art methods.

Contribution

The paper proposes a new text-3D generation framework integrating a knowledge graph, causal inference, and multi-layer transformer for enhanced 3D model synthesis from text.

Findings

Significant improvement in 3D generation quality.

Outperforms SOTA methods on text2shape datasets.

Effective multi-modal knowledge fusion enhances structural details.

Abstract

In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the ability of human beings to complement visual information details from ambiguous descriptions based on their own experience, we propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. In this process, we first introduce the text-3D knowledge graph to save the relationship between 3D models and textual semantic information, which can provide the related shapes to guide the target 3D model generation. Second, we integrate an effective causal inference model to select useful feature information from these related shapes, which removes the unrelated shape information and only maintains feature information that is strongly relevant to the textual description. Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.