3x2: 3D Object Part Segmentation by 2D Semantic Correspondences Article Swipe

PDF

Anh Thai , Wei‐Yao Wang , Hao Tang , Stefan Stojanov , Matt Feiszli , James M. Rehg ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2407.09648

3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating interesting part label transfer ability across different object categories. Project website: \url{https://ngailapdi.github.io/projects/3by2/}.

Related Topics

Segmentation Fault

Artificial Intelligence

Computer Vision

Computer Science

Concepts

Segmentation Artificial intelligence Object (grammar) Computer vision Computer science Natural language processing

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2407.09648
PDF: https://arxiv.org/pdf/2407.09648
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4400702722

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4400702722

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2407.09648

Digital Object Identifier
Title: 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-07-12

Full publication date if available
Authors: Anh Thai, Wei‐Yao Wang, Hao Tang, Stefan Stojanov, Matt Feiszli, James M. Rehg

List of authors in order
Landing page: https://arxiv.org/abs/2407.09648

Publisher landing page
PDF URL: https://arxiv.org/pdf/2407.09648

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2407.09648

Direct OA link when available
Concepts: Segmentation, Artificial intelligence, Object (grammar), Computer vision, Computer science, Natural language processing

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4400702722
doi	https://doi.org/10.48550/arxiv.2407.09648
ids.doi	https://doi.org/10.48550/arxiv.2407.09648
ids.openalex	https://openalex.org/W4400702722
fwci
type	preprint
title	3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10036
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9962000250816345
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Advanced Neural Network Applications
topics[1].id	https://openalex.org/T14339
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9939000010490417
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1707
topics[1].subfield.display_name	Computer Vision and Pattern Recognition
topics[1].display_name	Image Processing and 3D Reconstruction
topics[2].id	https://openalex.org/T12111
topics[2].field.id	https://openalex.org/fields/22
topics[2].field.display_name	Engineering
topics[2].score	0.9926000237464905
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/2209
topics[2].subfield.display_name	Industrial and Manufacturing Engineering
topics[2].display_name	Industrial Vision Systems and Defect Detection
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C89600930
concepts[0].level	2
concepts[0].score	0.7023360729217529
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1423946
concepts[0].display_name	Segmentation
concepts[1].id	https://openalex.org/C154945302
concepts[1].level	1
concepts[1].score	0.6804351806640625
concepts[1].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[1].display_name	Artificial intelligence
concepts[2].id	https://openalex.org/C2781238097
concepts[2].level	2
concepts[2].score	0.640470027923584
concepts[2].wikidata	https://www.wikidata.org/wiki/Q175026
concepts[2].display_name	Object (grammar)
concepts[3].id	https://openalex.org/C31972630
concepts[3].level	1
concepts[3].score	0.5788218379020691
concepts[3].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[3].display_name	Computer vision
concepts[4].id	https://openalex.org/C41008148
concepts[4].level	0
concepts[4].score	0.5678207874298096
concepts[4].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[4].display_name	Computer science
concepts[5].id	https://openalex.org/C204321447
concepts[5].level	1
concepts[5].score	0.4258444607257843
concepts[5].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[5].display_name	Natural language processing
keywords[0].id	https://openalex.org/keywords/segmentation
keywords[0].score	0.7023360729217529
keywords[0].display_name	Segmentation
keywords[1].id	https://openalex.org/keywords/artificial-intelligence
keywords[1].score	0.6804351806640625
keywords[1].display_name	Artificial intelligence
keywords[2].id	https://openalex.org/keywords/object
keywords[2].score	0.640470027923584
keywords[2].display_name	Object (grammar)
keywords[3].id	https://openalex.org/keywords/computer-vision
keywords[3].score	0.5788218379020691
keywords[3].display_name	Computer vision
keywords[4].id	https://openalex.org/keywords/computer-science
keywords[4].score	0.5678207874298096
keywords[4].display_name	Computer science
keywords[5].id	https://openalex.org/keywords/natural-language-processing
keywords[5].score	0.4258444607257843
keywords[5].display_name	Natural language processing
language	en
locations[0].id	pmh:oai:arXiv.org:2407.09648
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2407.09648
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2407.09648
locations[1].id	doi:10.48550/arxiv.2407.09648
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2407.09648
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5024590923
authorships[0].author.orcid	https://orcid.org/0000-0002-8134-5494
authorships[0].author.display_name	Anh Thai
authorships[0].author_position	first
authorships[0].raw_author_name	Thai, Anh
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5031992776
authorships[1].author.orcid	https://orcid.org/0000-0002-6551-1720
authorships[1].author.display_name	Wei‐Yao Wang
authorships[1].author_position	middle
authorships[1].raw_author_name	Wang, Weiyao
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5101745105
authorships[2].author.orcid	https://orcid.org/0000-0002-6197-0874
authorships[2].author.display_name	Hao Tang
authorships[2].author_position	middle
authorships[2].raw_author_name	Tang, Hao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5021585499
authorships[3].author.orcid
authorships[3].author.display_name	Stefan Stojanov
authorships[3].author_position	middle
authorships[3].raw_author_name	Stojanov, Stefan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5055620900
authorships[4].author.orcid
authorships[4].author.display_name	Matt Feiszli
authorships[4].author_position	middle
authorships[4].raw_author_name	Feiszli, Matt
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5002228469
authorships[5].author.orcid	https://orcid.org/0000-0003-1793-5462
authorships[5].author.display_name	James M. Rehg
authorships[5].author_position	last
authorships[5].raw_author_name	Rehg, James M.
authorships[5].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2407.09648
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10036
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9962000250816345
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Advanced Neural Network Applications
related_works	https://openalex.org/W2058170566, https://openalex.org/W2755342338, https://openalex.org/W2772917594, https://openalex.org/W2775347418, https://openalex.org/W2166024367, https://openalex.org/W3116076068, https://openalex.org/W2229312674, https://openalex.org/W2951359407, https://openalex.org/W2079911747, https://openalex.org/W1969923398
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2407.09648
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2407.09648
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2407.09648
primary_location.id	pmh:oai:arXiv.org:2407.09648
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2407.09648
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2407.09648
publication_date	2024-07-12
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	50
abstract_inverted_index.2D	17, 58, 112
abstract_inverted_index.3D	0, 22, 36, 53, 62, 106, 116
abstract_inverted_index.By	84
abstract_inverted_index.In	43
abstract_inverted_index.We	66
abstract_inverted_index.in	6, 16, 28
abstract_inverted_index.is	4
abstract_inverted_index.of	34, 104
abstract_inverted_index.on	77
abstract_inverted_index.or	55
abstract_inverted_index.to	31, 41, 48, 60, 100
abstract_inverted_index.we	46, 97
abstract_inverted_index.Our	108, 120
abstract_inverted_index.and	91, 94, 128
abstract_inverted_index.are	39, 98
abstract_inverted_index.can	123
abstract_inverted_index.due	30
abstract_inverted_index.few	51
abstract_inverted_index.has	13, 24
abstract_inverted_index.our	68
abstract_inverted_index.the	21, 32, 102
abstract_inverted_index.SOTA	75
abstract_inverted_index.able	99
abstract_inverted_index.been	14
abstract_inverted_index.from	87
abstract_inverted_index.less	26
abstract_inverted_index.made	15
abstract_inverted_index.part	2, 19, 29, 64, 118, 126, 132
abstract_inverted_index.that	73
abstract_inverted_index.this	44
abstract_inverted_index.with	80
abstract_inverted_index.While	10
abstract_inverted_index.label	133
abstract_inverted_index.novel	69
abstract_inverted_index.using	85
abstract_inverted_index.which	38
abstract_inverted_index.work,	45
abstract_inverted_index.3-By-2	72, 122
abstract_inverted_index.across	136
abstract_inverted_index.method	121
abstract_inverted_index.models	90
abstract_inverted_index.object	1, 18, 63, 117, 138
abstract_inverted_index.richly	56
abstract_inverted_index.shapes	54
abstract_inverted_index.termed	71
abstract_inverted_index.vision	8
abstract_inverted_index.Project	140
abstract_inverted_index.ability	135
abstract_inverted_index.labels,	113
abstract_inverted_index.levels.	83
abstract_inverted_index.limited	105
abstract_inverted_index.perform	61
abstract_inverted_index.present	67
abstract_inverted_index.propose	47
abstract_inverted_index.various	81, 125
abstract_inverted_index.achieves	74
abstract_inverted_index.approach	109
abstract_inverted_index.collect.	42
abstract_inverted_index.computer	7
abstract_inverted_index.datasets	59
abstract_inverted_index.enabling	114
abstract_inverted_index.features	86
abstract_inverted_index.leverage	49
abstract_inverted_index.overcome	101
abstract_inverted_index.progress	12
abstract_inverted_index.received	25
abstract_inverted_index.scarcity	33
abstract_inverted_index.semantic	93
abstract_inverted_index.transfer	134
abstract_inverted_index.website:	141
abstract_inverted_index.annotated	35, 52, 57
abstract_inverted_index.approach,	70
abstract_inverted_index.available	111
abstract_inverted_index.datasets,	37
abstract_inverted_index.different	78, 137
abstract_inverted_index.effective	115
abstract_inverted_index.essential	5
abstract_inverted_index.expensive	40
abstract_inverted_index.geometric	95
abstract_inverted_index.leverages	110
abstract_inverted_index.attention,	27
abstract_inverted_index.benchmarks	79
abstract_inverted_index.challenges	103
abstract_inverted_index.exploiting	92
abstract_inverted_index.foundation	89
abstract_inverted_index.pretrained	88
abstract_inverted_index.taxonomies	127
abstract_inverted_index.accommodate	124
abstract_inverted_index.categories.	139
abstract_inverted_index.counterpart	23
abstract_inverted_index.granularity	82
abstract_inverted_index.interesting	131
abstract_inverted_index.performance	76
abstract_inverted_index.substantial	11
abstract_inverted_index.annotations.	107
abstract_inverted_index.segmentation	3
abstract_inverted_index.applications.	9
abstract_inverted_index.demonstrating	130
abstract_inverted_index.segmentation,	20
abstract_inverted_index.segmentation.	65, 119
abstract_inverted_index.granularities,	129
abstract_inverted_index.correspondences,	96
abstract_inverted_index.\url{https://ngailapdi.github.io/projects/3by2/}.	142
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile