@inproceedings{huang-etal-2022-ladis,
title = "{LADIS}: Language Disentanglement for 3{D} Shape Editing",
author = "Huang, Ian and
Achlioptas, Panos and
Zhang, Tianyi and
Tulyakov, Sergei and
Sung, Minhyuk and
Guibas, Leonidas",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.404/",
doi = "10.18653/v1/2022.findings-emnlp.404",
pages = "5519--5532",
abstract = "Natural language interaction is a promising direction for democratizing 3D shape design. However, existing methods for text-driven 3D shape editing face challenges in producing decoupled, local edits to 3D shapes. We address this problem by learning disentangled latent representations that ground language in 3D geometry. To this end, we propose a complementary tool set including a novel network architecture, a disentanglement loss, and a new editing procedure. Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision. We show that our method outperforms existing SOTA methods by 20{\%} in terms of edit locality, and up to 6.6{\%} in terms of language reference resolution accuracy. Human evaluations additionally show that compared to the existing SOTA, our method produces shape edits that are more local, more semantically accurate, and more visually obvious. Our work suggests that by solely disentangling language representations, downstream 3D shape editing can become more local to relevant parts, even if the model was never given explicit part-based supervision."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-ladis">
<titleInfo>
<title>LADIS: Language Disentanglement for 3D Shape Editing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Panos</namePart>
<namePart type="family">Achlioptas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergei</namePart>
<namePart type="family">Tulyakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minhyuk</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonidas</namePart>
<namePart type="family">Guibas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural language interaction is a promising direction for democratizing 3D shape design. However, existing methods for text-driven 3D shape editing face challenges in producing decoupled, local edits to 3D shapes. We address this problem by learning disentangled latent representations that ground language in 3D geometry. To this end, we propose a complementary tool set including a novel network architecture, a disentanglement loss, and a new editing procedure. Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision. We show that our method outperforms existing SOTA methods by 20% in terms of edit locality, and up to 6.6% in terms of language reference resolution accuracy. Human evaluations additionally show that compared to the existing SOTA, our method produces shape edits that are more local, more semantically accurate, and more visually obvious. Our work suggests that by solely disentangling language representations, downstream 3D shape editing can become more local to relevant parts, even if the model was never given explicit part-based supervision.</abstract>
<identifier type="citekey">huang-etal-2022-ladis</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.404</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.404/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5519</start>
<end>5532</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LADIS: Language Disentanglement for 3D Shape Editing
%A Huang, Ian
%A Achlioptas, Panos
%A Zhang, Tianyi
%A Tulyakov, Sergei
%A Sung, Minhyuk
%A Guibas, Leonidas
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F huang-etal-2022-ladis
%X Natural language interaction is a promising direction for democratizing 3D shape design. However, existing methods for text-driven 3D shape editing face challenges in producing decoupled, local edits to 3D shapes. We address this problem by learning disentangled latent representations that ground language in 3D geometry. To this end, we propose a complementary tool set including a novel network architecture, a disentanglement loss, and a new editing procedure. Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision. We show that our method outperforms existing SOTA methods by 20% in terms of edit locality, and up to 6.6% in terms of language reference resolution accuracy. Human evaluations additionally show that compared to the existing SOTA, our method produces shape edits that are more local, more semantically accurate, and more visually obvious. Our work suggests that by solely disentangling language representations, downstream 3D shape editing can become more local to relevant parts, even if the model was never given explicit part-based supervision.
%R 10.18653/v1/2022.findings-emnlp.404
%U https://aclanthology.org/2022.findings-emnlp.404/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.404
%P 5519-5532
Markdown (Informal)
[LADIS: Language Disentanglement for 3D Shape Editing](https://aclanthology.org/2022.findings-emnlp.404/) (Huang et al., Findings 2022)
ACL
- Ian Huang, Panos Achlioptas, Tianyi Zhang, Sergei Tulyakov, Minhyuk Sung, and Leonidas Guibas. 2022. LADIS: Language Disentanglement for 3D Shape Editing. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 5519–5532, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.