@inproceedings{pang-shi-2025-forg3d,
title = "{FORG}3{D}: Flexible Object Rendering for Generating Vision-Language Spatial Reasoning Data from 3{D} Scenes",
author = "Pang, Oscar and
Shi, Freda",
editor = "Mishra, Pushkar and
Muresan, Smaranda and
Yu, Tao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-demo.36/",
doi = "10.18653/v1/2025.acl-demo.36",
pages = "376--384",
ISBN = "979-8-89176-253-4",
abstract = "We introduce FORG3D, a 3D rendering toolkit developed with Blender and Python, which synthesizes vision-language data for two primary purposes: (1) supporting human cognitive experiments that require fine-grained control over material and (2) analyzing and improving the visual reasoning capabilities of large vision-language models. The toolkit provides flexible and precise control over object placement, orientation, inter-object distances, and camera configurations while automatically generating detailed spatial metadata. Additionally, it includes a built-in feature for integrating AI-generated backgrounds, enhancing the realism of synthetic scenes. FORG3D is publicly available at https://github.com/compling-wat/FORG3D, and a video demonstration is available at https://www.youtube.com/watch?v=QvIqib{\_}PU8A."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pang-shi-2025-forg3d">
<titleInfo>
<title>FORG3D: Flexible Object Rendering for Generating Vision-Language Spatial Reasoning Data from 3D Scenes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Freda</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-253-4</identifier>
</relatedItem>
<abstract>We introduce FORG3D, a 3D rendering toolkit developed with Blender and Python, which synthesizes vision-language data for two primary purposes: (1) supporting human cognitive experiments that require fine-grained control over material and (2) analyzing and improving the visual reasoning capabilities of large vision-language models. The toolkit provides flexible and precise control over object placement, orientation, inter-object distances, and camera configurations while automatically generating detailed spatial metadata. Additionally, it includes a built-in feature for integrating AI-generated backgrounds, enhancing the realism of synthetic scenes. FORG3D is publicly available at https://github.com/compling-wat/FORG3D, and a video demonstration is available at https://www.youtube.com/watch?v=QvIqib_PU8A.</abstract>
<identifier type="citekey">pang-shi-2025-forg3d</identifier>
<identifier type="doi">10.18653/v1/2025.acl-demo.36</identifier>
<location>
<url>https://aclanthology.org/2025.acl-demo.36/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>376</start>
<end>384</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FORG3D: Flexible Object Rendering for Generating Vision-Language Spatial Reasoning Data from 3D Scenes
%A Pang, Oscar
%A Shi, Freda
%Y Mishra, Pushkar
%Y Muresan, Smaranda
%Y Yu, Tao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-253-4
%F pang-shi-2025-forg3d
%X We introduce FORG3D, a 3D rendering toolkit developed with Blender and Python, which synthesizes vision-language data for two primary purposes: (1) supporting human cognitive experiments that require fine-grained control over material and (2) analyzing and improving the visual reasoning capabilities of large vision-language models. The toolkit provides flexible and precise control over object placement, orientation, inter-object distances, and camera configurations while automatically generating detailed spatial metadata. Additionally, it includes a built-in feature for integrating AI-generated backgrounds, enhancing the realism of synthetic scenes. FORG3D is publicly available at https://github.com/compling-wat/FORG3D, and a video demonstration is available at https://www.youtube.com/watch?v=QvIqib_PU8A.
%R 10.18653/v1/2025.acl-demo.36
%U https://aclanthology.org/2025.acl-demo.36/
%U https://doi.org/10.18653/v1/2025.acl-demo.36
%P 376-384
Markdown (Informal)
[FORG3D: Flexible Object Rendering for Generating Vision-Language Spatial Reasoning Data from 3D Scenes](https://aclanthology.org/2025.acl-demo.36/) (Pang & Shi, ACL 2025)
ACL