MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation Article Swipe

PDF

Bangning Wei , Joshua Maraval , Meriem Outtas , Kidiyo Kpalma , Nicolas Ramin , Lu Zhang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.07519

The application of methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D GS) have steadily gained popularity in the field of 3D object segmentation in static scenes. These approaches demonstrate efficacy in a range of 3D scene understanding and editing tasks. Nevertheless, the 4D object segmentation of dynamic scenes remains an underexplored field due to the absence of a sufficiently extensive and accurately labelled multi-view video dataset. In this paper, we present MUVOD, a new multi-view video dataset for training and evaluating object segmentation in reconstructed real-world scenarios. The 17 selected scenes, describing various indoor or outdoor activities, are collected from different sources of datasets originating from various types of camera rigs. Each scene contains a minimum of 9 views and a maximum of 46 views. We provide 7830 RGB images (30 frames per video) with their corresponding segmentation mask in 4D motion, meaning that any object of interest in the scene could be tracked across temporal frames of a given view or across different views belonging to the same camera rig. This dataset, which contains 459 instances of 73 categories, is intended as a basic benchmark for the evaluation of multi-view video segmentation methods. We also present an evaluation metric and a baseline segmentation approach to encourage and evaluate progress in this evolving field. Additionally, we propose a new benchmark for 3D object segmentation task with a subset of annotated multi-view images selected from our MUVOD dataset. This subset contains 50 objects of different conditions in different scenarios, providing a more comprehensive analysis of state-of-the-art 3D object segmentation methods. Our proposed MUVOD dataset is available at https://volumetric-repository.labs.b-com.com/#/muvod.

Related Topics

The Three-Body Problem (Novel)

Persuasion (Novel)

Hyperion (Simmons Novel)

Overlord (Novel Series)

The Institute (King Novel)

The Outsiders (Novel)

Warriors (Novel Series)

The Fireman (Novel)

The Phantom Of The Opera (Novel)

Holes (Novel)

Atonement (Novel)

I Know What You Did Last Summer (Novel)

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2507.07519
PDF: https://arxiv.org/pdf/2507.07519
OA Status: green
OpenAlex ID: https://openalex.org/W4416307810

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416307810

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2507.07519

Digital Object Identifier
Title: MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-10

Full publication date if available
Authors: Bangning Wei, Joshua Maraval, Meriem Outtas, Kidiyo Kpalma, Nicolas Ramin, Lu Zhang

List of authors in order
Landing page: https://arxiv.org/abs/2507.07519

Publisher landing page
PDF URL: https://arxiv.org/pdf/2507.07519

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/2507.07519

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416307810
doi	https://doi.org/10.48550/arxiv.2507.07519
ids.doi	https://doi.org/10.48550/arxiv.2507.07519
ids.openalex	https://openalex.org/W4416307810
fwci
type	preprint
title	MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2507.07519
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/2507.07519
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/2507.07519
locations[1].id	doi:10.48550/arxiv.2507.07519
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
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
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.2507.07519
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5109750665
authorships[0].author.orcid	https://orcid.org/0000-0002-2308-9920
authorships[0].author.display_name	Bangning Wei
authorships[0].author_position	first
authorships[0].raw_author_name	Wei, Bangning
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5104939511
authorships[1].author.orcid
authorships[1].author.display_name	Joshua Maraval
authorships[1].author_position	middle
authorships[1].raw_author_name	Maraval, Joshua
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5041258744
authorships[2].author.orcid	https://orcid.org/0000-0002-0918-1990
authorships[2].author.display_name	Meriem Outtas
authorships[2].author_position	middle
authorships[2].raw_author_name	Outtas, Meriem
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5029409871
authorships[3].author.orcid	https://orcid.org/0000-0001-8179-6415
authorships[3].author.display_name	Kidiyo Kpalma
authorships[3].author_position	middle
authorships[3].raw_author_name	Kpalma, Kidiyo
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5092705442
authorships[4].author.orcid
authorships[4].author.display_name	Nicolas Ramin
authorships[4].author_position	middle
authorships[4].raw_author_name	Ramin, Nicolas
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5035359666
authorships[5].author.orcid	https://orcid.org/0000-0002-8859-5453
authorships[5].author.display_name	Lu Zhang
authorships[5].author_position	last
authorships[5].raw_author_name	Zhang, Lu
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/2507.07519
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T10:52:38.981891
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2507.07519
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/2507.07519
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/2507.07519
primary_location.id	pmh:oai:arXiv.org:2507.07519
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/2507.07519
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/2507.07519
publication_date	2025-07-10
publication_year	2025
referenced_works_count	0
abstract_inverted_index.9	121
abstract_inverted_index.a	35, 61, 76, 118, 124, 162, 187, 205, 221, 230, 253
abstract_inverted_index.17	92
abstract_inverted_index.3D	11, 24, 38, 225, 259
abstract_inverted_index.46	127
abstract_inverted_index.4D	46, 144
abstract_inverted_index.50	244
abstract_inverted_index.73	182
abstract_inverted_index.In	70
abstract_inverted_index.We	129, 198
abstract_inverted_index.an	53, 201
abstract_inverted_index.as	186
abstract_inverted_index.at	269
abstract_inverted_index.be	156
abstract_inverted_index.in	20, 27, 34, 87, 143, 152, 214, 249
abstract_inverted_index.is	184, 267
abstract_inverted_index.of	2, 23, 37, 49, 60, 106, 112, 120, 126, 150, 161, 181, 193, 232, 246, 257
abstract_inverted_index.on	5
abstract_inverted_index.or	98, 165
abstract_inverted_index.to	57, 170, 209
abstract_inverted_index.we	73, 219
abstract_inverted_index.(30	134
abstract_inverted_index.(3D	14
abstract_inverted_index.459	179
abstract_inverted_index.GS)	15
abstract_inverted_index.Our	263
abstract_inverted_index.RGB	132
abstract_inverted_index.The	0, 91
abstract_inverted_index.and	10, 41, 64, 83, 123, 204, 211
abstract_inverted_index.any	148
abstract_inverted_index.are	101
abstract_inverted_index.due	56
abstract_inverted_index.for	81, 190, 224
abstract_inverted_index.new	77, 222
abstract_inverted_index.our	238
abstract_inverted_index.per	136
abstract_inverted_index.the	21, 45, 58, 153, 171, 191
abstract_inverted_index.7830	131
abstract_inverted_index.Each	115
abstract_inverted_index.This	175, 241
abstract_inverted_index.also	199
abstract_inverted_index.from	103, 109, 237
abstract_inverted_index.have	16
abstract_inverted_index.mask	142
abstract_inverted_index.more	254
abstract_inverted_index.rig.	174
abstract_inverted_index.same	172
abstract_inverted_index.task	228
abstract_inverted_index.that	147
abstract_inverted_index.this	71, 215
abstract_inverted_index.view	164
abstract_inverted_index.with	138, 229
abstract_inverted_index.MUVOD	239, 265
abstract_inverted_index.These	30
abstract_inverted_index.based	4
abstract_inverted_index.basic	188
abstract_inverted_index.could	155
abstract_inverted_index.field	22, 55
abstract_inverted_index.given	163
abstract_inverted_index.range	36
abstract_inverted_index.rigs.	114
abstract_inverted_index.scene	39, 116, 154
abstract_inverted_index.their	139
abstract_inverted_index.types	111
abstract_inverted_index.video	68, 79, 195
abstract_inverted_index.views	122, 168
abstract_inverted_index.which	177
abstract_inverted_index.(NeRF)	9
abstract_inverted_index.Fields	8
abstract_inverted_index.MUVOD,	75
abstract_inverted_index.Neural	6
abstract_inverted_index.across	158, 166
abstract_inverted_index.camera	113, 173
abstract_inverted_index.field.	217
abstract_inverted_index.frames	135, 160
abstract_inverted_index.gained	18
abstract_inverted_index.images	133, 235
abstract_inverted_index.indoor	97
abstract_inverted_index.metric	203
abstract_inverted_index.object	25, 47, 85, 149, 226, 260
abstract_inverted_index.paper,	72
abstract_inverted_index.scenes	51
abstract_inverted_index.static	28
abstract_inverted_index.subset	231, 242
abstract_inverted_index.tasks.	43
abstract_inverted_index.video)	137
abstract_inverted_index.views.	128
abstract_inverted_index.absence	59
abstract_inverted_index.dataset	80, 266
abstract_inverted_index.dynamic	50
abstract_inverted_index.editing	42
abstract_inverted_index.maximum	125
abstract_inverted_index.meaning	146
abstract_inverted_index.methods	3
abstract_inverted_index.minimum	119
abstract_inverted_index.motion,	145
abstract_inverted_index.objects	245
abstract_inverted_index.outdoor	99
abstract_inverted_index.present	74, 200
abstract_inverted_index.propose	220
abstract_inverted_index.provide	130
abstract_inverted_index.remains	52
abstract_inverted_index.scenes,	94
abstract_inverted_index.scenes.	29
abstract_inverted_index.sources	105
abstract_inverted_index.tracked	157
abstract_inverted_index.various	96, 110
abstract_inverted_index.Gaussian	12
abstract_inverted_index.Radiance	7
abstract_inverted_index.analysis	256
abstract_inverted_index.approach	208
abstract_inverted_index.baseline	206
abstract_inverted_index.contains	117, 178, 243
abstract_inverted_index.dataset,	176
abstract_inverted_index.dataset.	69, 240
abstract_inverted_index.datasets	107
abstract_inverted_index.efficacy	33
abstract_inverted_index.evaluate	212
abstract_inverted_index.evolving	216
abstract_inverted_index.intended	185
abstract_inverted_index.interest	151
abstract_inverted_index.labelled	66
abstract_inverted_index.methods.	197, 262
abstract_inverted_index.progress	213
abstract_inverted_index.proposed	264
abstract_inverted_index.selected	93, 236
abstract_inverted_index.steadily	17
abstract_inverted_index.temporal	159
abstract_inverted_index.training	82
abstract_inverted_index.Splatting	13
abstract_inverted_index.annotated	233
abstract_inverted_index.available	268
abstract_inverted_index.belonging	169
abstract_inverted_index.benchmark	189, 223
abstract_inverted_index.collected	102
abstract_inverted_index.different	104, 167, 247, 250
abstract_inverted_index.encourage	210
abstract_inverted_index.extensive	63
abstract_inverted_index.instances	180
abstract_inverted_index.providing	252
abstract_inverted_index.accurately	65
abstract_inverted_index.approaches	31
abstract_inverted_index.conditions	248
abstract_inverted_index.describing	95
abstract_inverted_index.evaluating	84
abstract_inverted_index.evaluation	192, 202
abstract_inverted_index.multi-view	67, 78, 194, 234
abstract_inverted_index.popularity	19
abstract_inverted_index.real-world	89
abstract_inverted_index.scenarios,	251
abstract_inverted_index.scenarios.	90
abstract_inverted_index.activities,	100
abstract_inverted_index.application	1
abstract_inverted_index.categories,	183
abstract_inverted_index.demonstrate	32
abstract_inverted_index.originating	108
abstract_inverted_index.segmentation	26, 48, 86, 141, 196, 207, 227, 261
abstract_inverted_index.sufficiently	62
abstract_inverted_index.Additionally,	218
abstract_inverted_index.Nevertheless,	44
abstract_inverted_index.comprehensive	255
abstract_inverted_index.corresponding	140
abstract_inverted_index.reconstructed	88
abstract_inverted_index.underexplored	54
abstract_inverted_index.understanding	40
abstract_inverted_index.state-of-the-art	258
abstract_inverted_index.https://volumetric-repository.labs.b-com.com/#/muvod.	270
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile