Skip to main content

Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

Author(s): Chen, Kevin; Choy, Christopher B; Savva, Manolis; Chang, Angel X; Funkhouser, Thomas; et al

To refer to this page use:
Abstract: We present a method for generating colored 3D shapes from natural language. To this end, we first learn joint embeddings of freeform text descriptions and colored 3D shapes. Our model combines and extends learning by association and metric learning approaches to learn implicit cross-modal connections, and produces a joint representation that captures the many-to-many relations between language and physical properties of 3D shapes such as color and shape. To evaluate our approach, we collect a large dataset of natural language descriptions for physical 3D objects in the ShapeNet dataset. With this learned joint embedding we demonstrate text-to-shape retrieval that outperforms baseline approaches. Using our embeddings with a novel conditional Wasserstein GAN framework, we generate colored 3D shapes from text. Our method is the first to connect natural language text with realistic 3D objects exhibiting rich variations in color, texture, and shape detail.
Publication Date: 2019
Citation: Chen, Kevin, Christopher B. Choy, Manolis Savva, Angel X. Chang, Thomas Funkhouser, and Silvio Savarese. "Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings." In Asian Conference on Computer Vision (2019): pp. 100-116. doi:10.1007/978-3-030-20893-6_7
DOI: 10.1007/978-3-030-20893-6_7
ISSN: 0302-9743
EISSN: 1611-3349
Pages: 100 - 116
Type of Material: Conference Article
Journal/Proceeding Title: Asian Conference on Computer Vision
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.