S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix Article Swipe

PDF

Peng Dai , Feitong Tan , Qiangeng Xu , David Futschik , Ruofei Du , Yinda Zhang , Xiaojuan Qi ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2508.08048

While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method that leverages an off-the-shelf monocular video generation model to produce immersive 3D videos. Our approach first warps the generated monocular video into pre-defined camera viewpoints using estimated depth information, then applies a novel \textit{frame matrix} inpainting framework. This framework utilizes the original video generation model to synthesize missing content across different viewpoints and timestamps, ensuring spatial and temporal consistency without requiring additional model fine-tuning. Moreover, we develop a \dualupdate~scheme that further improves the quality of video inpainting by alleviating the negative effects propagated from disoccluded areas in the latent space. The resulting multi-view videos are then adapted into stereoscopic pairs or optimized into 4D Gaussians for spatial video synthesis. We validate the efficacy of our proposed method by conducting experiments on videos from various generative models, such as Sora, Lumiere, WALT, and Zeroscope. The experiments demonstrate that our method has a significant improvement over previous methods. Project page at: https://daipengwa.github.io/S-2VG_ProjectPage/

Related Topics

Nintendo Video Game Consoles

Vicky Vidya Ka Woh Wala Video

Fallout (Video Game)

Tales (Video Game Series)

Grand Theft Auto (Video Game)

Portal (Video Game)

Dayz (Video Game)

Max Payne (Video Game)

Destiny (Video Game)

Dragon Quest (Video Game)

Dante's Inferno (Video Game)

Animal Crossing (Video Game)

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2508.08048
PDF: https://arxiv.org/pdf/2508.08048
OA Status: green
OpenAlex ID: https://openalex.org/W4416243189

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416243189

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2508.08048

Digital Object Identifier
Title: S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-08-11

Full publication date if available
Authors: Peng Dai, Feitong Tan, Qiangeng Xu, David Futschik, Ruofei Du, Yinda Zhang, Xiaojuan Qi

List of authors in order
Landing page: https://arxiv.org/abs/2508.08048

Publisher landing page
PDF URL: https://arxiv.org/pdf/2508.08048

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/2508.08048

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416243189
doi	https://doi.org/10.48550/arxiv.2508.08048
ids.doi	https://doi.org/10.48550/arxiv.2508.08048
ids.openalex	https://openalex.org/W4416243189
fwci
type	preprint
title	S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
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:2508.08048
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/2508.08048
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/2508.08048
locations[1].id	doi:10.48550/arxiv.2508.08048
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.2508.08048
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101406874
authorships[0].author.orcid	https://orcid.org/0000-0002-9004-2591
authorships[0].author.display_name	Peng Dai
authorships[0].author_position	first
authorships[0].raw_author_name	Dai, Peng
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5025919556
authorships[1].author.orcid	https://orcid.org/0000-0002-7606-1331
authorships[1].author.display_name	Feitong Tan
authorships[1].author_position	middle
authorships[1].raw_author_name	Tan, Feitong
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5030369632
authorships[2].author.orcid
authorships[2].author.display_name	Qiangeng Xu
authorships[2].author_position	middle
authorships[2].raw_author_name	Xu, Qiangeng
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5024003627
authorships[3].author.orcid	https://orcid.org/0000-0003-3254-0290
authorships[3].author.display_name	David Futschik
authorships[3].author_position	middle
authorships[3].raw_author_name	Futschik, David
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5001822106
authorships[4].author.orcid	https://orcid.org/0000-0003-2471-9776
authorships[4].author.display_name	Ruofei Du
authorships[4].author_position	middle
authorships[4].raw_author_name	Du, Ruofei
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5064561875
authorships[5].author.orcid
authorships[5].author.display_name	Yinda Zhang
authorships[5].author_position	middle
authorships[5].raw_author_name	Zhang, Yinda
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5102498323
authorships[6].author.orcid	https://orcid.org/0000-0002-4285-1626
authorships[6].author.display_name	Xiaojuan Qi
authorships[6].author_position	middle
authorships[6].raw_author_name	Qi, Xiaojuan
authorships[6].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/2508.08048
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	S^2VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T09:07:17.944850
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2508.08048
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/2508.08048
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/2508.08048
primary_location.id	pmh:oai:arXiv.org:2508.08048
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/2508.08048
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/2508.08048
publication_date	2025-08-11
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	25, 61, 97, 170
abstract_inverted_index.3D	11, 41
abstract_inverted_index.4D	133
abstract_inverted_index.We	23, 139
abstract_inverted_index.an	20, 32
abstract_inverted_index.as	157
abstract_inverted_index.at	5
abstract_inverted_index.by	107, 147
abstract_inverted_index.in	116
abstract_inverted_index.of	104, 143
abstract_inverted_index.on	150
abstract_inverted_index.or	130
abstract_inverted_index.to	38, 75
abstract_inverted_index.we	95
abstract_inverted_index.Our	43
abstract_inverted_index.The	120, 163
abstract_inverted_index.and	13, 27, 82, 86, 161
abstract_inverted_index.are	124
abstract_inverted_index.at:	178
abstract_inverted_index.for	16, 135
abstract_inverted_index.has	169
abstract_inverted_index.our	144, 167
abstract_inverted_index.the	47, 70, 102, 109, 117, 141
abstract_inverted_index.This	67
abstract_inverted_index.from	113, 152
abstract_inverted_index.into	51, 127, 132
abstract_inverted_index.over	173
abstract_inverted_index.page	177
abstract_inverted_index.such	156
abstract_inverted_index.that	30, 99, 166
abstract_inverted_index.then	59, 125
abstract_inverted_index.Sora,	158
abstract_inverted_index.WALT,	160
abstract_inverted_index.While	0
abstract_inverted_index.areas	115
abstract_inverted_index.depth	57
abstract_inverted_index.excel	4
abstract_inverted_index.first	45
abstract_inverted_index.model	37, 74, 92
abstract_inverted_index.novel	62
abstract_inverted_index.pairs	129
abstract_inverted_index.using	55
abstract_inverted_index.video	1, 35, 50, 72, 105, 137
abstract_inverted_index.warps	46
abstract_inverted_index.across	79
abstract_inverted_index.camera	53
abstract_inverted_index.latent	118
abstract_inverted_index.method	29, 146, 168
abstract_inverted_index.models	3
abstract_inverted_index.space.	119
abstract_inverted_index.videos	15, 123, 151
abstract_inverted_index.Project	176
abstract_inverted_index.adapted	126
abstract_inverted_index.applies	60
abstract_inverted_index.content	78
abstract_inverted_index.develop	96
abstract_inverted_index.effects	111
abstract_inverted_index.further	100
abstract_inverted_index.matrix}	64
abstract_inverted_index.missing	77
abstract_inverted_index.models,	155
abstract_inverted_index.present	24
abstract_inverted_index.produce	39
abstract_inverted_index.quality	103
abstract_inverted_index.remains	19
abstract_inverted_index.spatial	14, 85, 136
abstract_inverted_index.various	153
abstract_inverted_index.videos,	9
abstract_inverted_index.videos.	42
abstract_inverted_index.without	89
abstract_inverted_index.Lumiere,	159
abstract_inverted_index.approach	44
abstract_inverted_index.efficacy	142
abstract_inverted_index.ensuring	84
abstract_inverted_index.improves	101
abstract_inverted_index.methods.	175
abstract_inverted_index.negative	110
abstract_inverted_index.original	71
abstract_inverted_index.previous	174
abstract_inverted_index.proposed	145
abstract_inverted_index.temporal	87
abstract_inverted_index.utilizes	69
abstract_inverted_index.validate	140
abstract_inverted_index.Gaussians	134
abstract_inverted_index.Moreover,	94
abstract_inverted_index.different	80
abstract_inverted_index.estimated	56
abstract_inverted_index.framework	68
abstract_inverted_index.generated	48
abstract_inverted_index.immersive	17, 40
abstract_inverted_index.leverages	31
abstract_inverted_index.monocular	8, 34, 49
abstract_inverted_index.optimized	131
abstract_inverted_index.pose-free	26
abstract_inverted_index.producing	6
abstract_inverted_index.requiring	90
abstract_inverted_index.resulting	121
abstract_inverted_index.Zeroscope.	162
abstract_inverted_index.additional	91
abstract_inverted_index.challenge.	22
abstract_inverted_index.conducting	148
abstract_inverted_index.framework.	66
abstract_inverted_index.generating	10
abstract_inverted_index.generation	2, 36, 73
abstract_inverted_index.generative	154
abstract_inverted_index.inpainting	65, 106
abstract_inverted_index.multi-view	122
abstract_inverted_index.propagated	112
abstract_inverted_index.synthesis.	138
abstract_inverted_index.synthesize	76
abstract_inverted_index.viewpoints	54, 81
abstract_inverted_index.alleviating	108
abstract_inverted_index.consistency	88
abstract_inverted_index.demonstrate	165
abstract_inverted_index.disoccluded	114
abstract_inverted_index.experiments	149, 164
abstract_inverted_index.improvement	172
abstract_inverted_index.pre-defined	52
abstract_inverted_index.significant	171
abstract_inverted_index.timestamps,	83
abstract_inverted_index.applications	18
abstract_inverted_index.fine-tuning.	93
abstract_inverted_index.high-quality	7
abstract_inverted_index.information,	58
abstract_inverted_index.stereoscopic	12, 128
abstract_inverted_index.\textit{frame	63
abstract_inverted_index.off-the-shelf	33
abstract_inverted_index.training-free	28
abstract_inverted_index.underexplored	21
abstract_inverted_index.\dualupdate~scheme	98
abstract_inverted_index.https://daipengwa.github.io/S-2VG_ProjectPage/	179
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	7
citation_normalized_percentile