@inproceedings{0399c6a428354754aebf6fa2a003bcc0,
title = "Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings",
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.",
author = "Kevin Chen and Choy, {Christopher B.} and Manolis Savva and Chang, {Angel X.} and Thomas Funkhouser and Silvio Savarese",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Switzerland AG.; 14th Asian Conference on Computer Vision, ACCV 2018 ; Conference date: 02-12-2018 Through 06-12-2018",
year = "2019",
doi = "10.1007/978-3-030-20893-6_7",
language = "English (US)",
isbn = "9783030208929",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "100--116",
editor = "Hongdong Li and C.V. Jawahar and Konrad Schindler and Greg Mori",
booktitle = "Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, Revised Selected Papers",
address = "Germany",
}