Towards Implicit Text-Guided 3D Shape Generation

TL;DR

This paper introduces a novel method for generating high-fidelity 3D shapes from text descriptions, incorporating shape-color decoupling, word-level spatial transformers, cyclic loss, and shape IMLE for diversity, with extensions for shape manipulation.

Contribution

It presents a new approach that improves text-guided 3D shape generation by decoupling shape and color, and introduces techniques for diversity and manipulation.

Findings

Outperforms existing methods on large text-shape benchmark

Generates high-fidelity, color-matching 3D shapes from text

Enables effective shape manipulation based on text input

Abstract

In this work, we explore the challenging task of generating 3D shapes from text. Beyond the existing works, we propose a new approach for text-guided 3D shape generation, capable of producing high-fidelity shapes with colors that match the given text description. This work has several technical contributions. First, we decouple the shape and color predictions for learning features in both texts and shapes, and propose the word-level spatial transformer to correlate word features from text with spatial features from shape. Also, we design a cyclic loss to encourage consistency between text and shape, and introduce the shape IMLE to diversify the generated shapes. Further, we extend the framework to enable text-guided shape manipulation. Extensive experiments on the largest existing text-shape benchmark manifest the superiority of this work. The code and the models are available at https://github.com/liuzhengzhe/Towards-Implicit Text-Guided-Shape-Generation.