A Dataset for Mechanical Mechanisms

This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and 3D sketches, meticulously curated to ensure relevance and q...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ghezelbash, Farshid, Eskandari, Amir Hossein, Bidhendi, Amir J
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Ghezelbash, Farshid
Eskandari, Amir Hossein
Bidhendi, Amir J
description This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and 3D sketches, meticulously curated to ensure relevance and quality. We demonstrate the application of this dataset by fine-tuning two models: 1) Stable Diffusion (for generating new mechanical designs), and 2) BLIP-2 (for captioning these designs). While the results from Stable Diffusion show promise, particularly in generating coherent 3D sketches, the model struggles with 2D sketches and occasionally produces nonsensical outputs. These limitations underscore the need for further development, particularly in expanding the dataset and refining model architectures. Nonetheless, this work serves as a step towards leveraging generative AI in mechanical design, highlighting both the potential and current limitations of these approaches.
doi_str_mv 10.48550/arxiv.2409.03763
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2409_03763</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2409_03763</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2409_037633</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjGw1DMwNjcz5mRQdlRwSSxJLE4tUUjLL1LwTU3OSMzLTE7MgTGLc4t5GFjTEnOKU3mhNDeDvJtriLOHLti4-IKizNzEosp4kLHxYGONCasAAFd5K3g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Dataset for Mechanical Mechanisms</title><source>arXiv.org</source><creator>Ghezelbash, Farshid ; Eskandari, Amir Hossein ; Bidhendi, Amir J</creator><creatorcontrib>Ghezelbash, Farshid ; Eskandari, Amir Hossein ; Bidhendi, Amir J</creatorcontrib><description>This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and 3D sketches, meticulously curated to ensure relevance and quality. We demonstrate the application of this dataset by fine-tuning two models: 1) Stable Diffusion (for generating new mechanical designs), and 2) BLIP-2 (for captioning these designs). While the results from Stable Diffusion show promise, particularly in generating coherent 3D sketches, the model struggles with 2D sketches and occasionally produces nonsensical outputs. These limitations underscore the need for further development, particularly in expanding the dataset and refining model architectures. Nonetheless, this work serves as a step towards leveraging generative AI in mechanical design, highlighting both the potential and current limitations of these approaches.</description><identifier>DOI: 10.48550/arxiv.2409.03763</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-08</creationdate><rights>http://creativecommons.org/publicdomain/zero/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2409.03763$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2409.03763$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Ghezelbash, Farshid</creatorcontrib><creatorcontrib>Eskandari, Amir Hossein</creatorcontrib><creatorcontrib>Bidhendi, Amir J</creatorcontrib><title>A Dataset for Mechanical Mechanisms</title><description>This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and 3D sketches, meticulously curated to ensure relevance and quality. We demonstrate the application of this dataset by fine-tuning two models: 1) Stable Diffusion (for generating new mechanical designs), and 2) BLIP-2 (for captioning these designs). While the results from Stable Diffusion show promise, particularly in generating coherent 3D sketches, the model struggles with 2D sketches and occasionally produces nonsensical outputs. These limitations underscore the need for further development, particularly in expanding the dataset and refining model architectures. Nonetheless, this work serves as a step towards leveraging generative AI in mechanical design, highlighting both the potential and current limitations of these approaches.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjGw1DMwNjcz5mRQdlRwSSxJLE4tUUjLL1LwTU3OSMzLTE7MgTGLc4t5GFjTEnOKU3mhNDeDvJtriLOHLti4-IKizNzEosp4kLHxYGONCasAAFd5K3g</recordid><startdate>20240819</startdate><enddate>20240819</enddate><creator>Ghezelbash, Farshid</creator><creator>Eskandari, Amir Hossein</creator><creator>Bidhendi, Amir J</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240819</creationdate><title>A Dataset for Mechanical Mechanisms</title><author>Ghezelbash, Farshid ; Eskandari, Amir Hossein ; Bidhendi, Amir J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2409_037633</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Ghezelbash, Farshid</creatorcontrib><creatorcontrib>Eskandari, Amir Hossein</creatorcontrib><creatorcontrib>Bidhendi, Amir J</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ghezelbash, Farshid</au><au>Eskandari, Amir Hossein</au><au>Bidhendi, Amir J</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Dataset for Mechanical Mechanisms</atitle><date>2024-08-19</date><risdate>2024</risdate><abstract>This study introduces a dataset consisting of approximately 9,000 images of mechanical mechanisms and their corresponding descriptions, aimed at supporting research in mechanism design. The dataset consists of a diverse collection of 2D and 3D sketches, meticulously curated to ensure relevance and quality. We demonstrate the application of this dataset by fine-tuning two models: 1) Stable Diffusion (for generating new mechanical designs), and 2) BLIP-2 (for captioning these designs). While the results from Stable Diffusion show promise, particularly in generating coherent 3D sketches, the model struggles with 2D sketches and occasionally produces nonsensical outputs. These limitations underscore the need for further development, particularly in expanding the dataset and refining model architectures. Nonetheless, this work serves as a step towards leveraging generative AI in mechanical design, highlighting both the potential and current limitations of these approaches.</abstract><doi>10.48550/arxiv.2409.03763</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2409.03763
ispartof
issn
language eng
recordid cdi_arxiv_primary_2409_03763
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title A Dataset for Mechanical Mechanisms
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T00%3A48%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Dataset%20for%20Mechanical%20Mechanisms&rft.au=Ghezelbash,%20Farshid&rft.date=2024-08-19&rft_id=info:doi/10.48550/arxiv.2409.03763&rft_dat=%3Carxiv_GOX%3E2409_03763%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true