CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models Article Swipe

PDF

Hao He , Ceyuan Yang , Shanchuan Lin , Yinghao Xu , Teng Wei , Liangke Gui , Qi Zhao , Gordon Wetzstein , Lu Jiang , Hongsheng Li ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.10592

This paper introduces CameraCtrl II, a framework that enables large-scale dynamic scene exploration through a camera-controlled video diffusion model. Previous camera-conditioned video generative models suffer from diminished video dynamics and limited range of viewpoints when generating videos with large camera movement. We take an approach that progressively expands the generation of dynamic scenes -- first enhancing dynamic content within individual video clip, then extending this capability to create seamless explorations across broad viewpoint ranges. Specifically, we construct a dataset featuring a large degree of dynamics with camera parameter annotations for training while designing a lightweight camera injection module and training scheme to preserve dynamics of the pretrained models. Building on these improved single-clip techniques, we enable extended scene exploration by allowing users to iteratively specify camera trajectories for generating coherent video sequences. Experiments across diverse scenarios demonstrate that CameraCtrl Ii enables camera-controlled dynamic scene synthesis with substantially wider spatial exploration than previous approaches.

Related Topics

Dynamic Random-Access Memory

Roundhay Garden Scene

Dynamic Time Warping

Selena Gomez & The Scene

Palm Desert Scene

Scene Graph

Dynamic Web Page

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2503.10592
PDF: https://arxiv.org/pdf/2503.10592
OA Status: green
OpenAlex ID: https://openalex.org/W4416040271

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416040271

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2503.10592

Digital Object Identifier
Title: CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-13

Full publication date if available
Authors: Hao He, Ceyuan Yang, Shanchuan Lin, Yinghao Xu, Teng Wei, Liangke Gui, Qi Zhao, Gordon Wetzstein, Lu Jiang, Hongsheng Li

List of authors in order
Landing page: https://arxiv.org/abs/2503.10592

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.10592

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/2503.10592

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416040271
doi	https://doi.org/10.48550/arxiv.2503.10592
ids.doi	https://doi.org/10.48550/arxiv.2503.10592
ids.openalex	https://openalex.org/W4416040271
fwci
type	preprint
title	CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
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:2503.10592
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/2503.10592
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/2503.10592
locations[1].id	doi:10.48550/arxiv.2503.10592
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.2503.10592
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5100382845
authorships[0].author.orcid	https://orcid.org/0000-0001-8074-746X
authorships[0].author.display_name	Hao He
authorships[0].author_position	first
authorships[0].raw_author_name	He, Hao
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5025976462
authorships[1].author.orcid	https://orcid.org/0000-0003-1417-1938
authorships[1].author.display_name	Ceyuan Yang
authorships[1].author_position	middle
authorships[1].raw_author_name	Yang, Ceyuan
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5048135392
authorships[2].author.orcid
authorships[2].author.display_name	Shanchuan Lin
authorships[2].author_position	middle
authorships[2].raw_author_name	Lin, Shanchuan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5019024625
authorships[3].author.orcid	https://orcid.org/0000-0003-2696-9664
authorships[3].author.display_name	Yinghao Xu
authorships[3].author_position	middle
authorships[3].raw_author_name	Xu, Yinghao
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5091543899
authorships[4].author.orcid	https://orcid.org/0000-0003-3860-200X
authorships[4].author.display_name	Teng Wei
authorships[4].author_position	middle
authorships[4].raw_author_name	Wei, Meng
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5037727565
authorships[5].author.orcid
authorships[5].author.display_name	Liangke Gui
authorships[5].author_position	middle
authorships[5].raw_author_name	Gui, Liangke
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5047419128
authorships[6].author.orcid	https://orcid.org/0000-0003-3054-8934
authorships[6].author.display_name	Qi Zhao
authorships[6].author_position	middle
authorships[6].raw_author_name	Zhao, Qi
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5014044649
authorships[7].author.orcid	https://orcid.org/0000-0002-9243-6885
authorships[7].author.display_name	Gordon Wetzstein
authorships[7].author_position	middle
authorships[7].raw_author_name	Wetzstein, Gordon
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5090730336
authorships[8].author.orcid	https://orcid.org/0000-0003-0286-8439
authorships[8].author.display_name	Lu Jiang
authorships[8].author_position	middle
authorships[8].raw_author_name	Jiang, Lu
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5100732450
authorships[9].author.orcid	https://orcid.org/0000-0002-2664-7975
authorships[9].author.display_name	Hongsheng Li
authorships[9].author_position	last
authorships[9].raw_author_name	Li, Hongsheng
authorships[9].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/2503.10592
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models
has_fulltext	False
is_retracted	False
updated_date	2025-11-09T23:09:16.995542
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2503.10592
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/2503.10592
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/2503.10592
primary_location.id	pmh:oai:arXiv.org:2503.10592
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/2503.10592
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/2503.10592
publication_date	2025-03-13
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	5, 14, 77, 80, 93
abstract_inverted_index.--	53
abstract_inverted_index.Ii	139
abstract_inverted_index.We	41
abstract_inverted_index.an	43
abstract_inverted_index.by	119
abstract_inverted_index.of	32, 50, 83, 104
abstract_inverted_index.on	109
abstract_inverted_index.to	66, 101, 122
abstract_inverted_index.we	75, 114
abstract_inverted_index.II,	4
abstract_inverted_index.and	29, 98
abstract_inverted_index.for	89, 127
abstract_inverted_index.the	48, 105
abstract_inverted_index.This	0
abstract_inverted_index.from	25
abstract_inverted_index.take	42
abstract_inverted_index.than	150
abstract_inverted_index.that	7, 45, 137
abstract_inverted_index.then	62
abstract_inverted_index.this	64
abstract_inverted_index.when	34
abstract_inverted_index.with	37, 85, 145
abstract_inverted_index.broad	71
abstract_inverted_index.clip,	61
abstract_inverted_index.first	54
abstract_inverted_index.large	38, 81
abstract_inverted_index.paper	1
abstract_inverted_index.range	31
abstract_inverted_index.scene	11, 117, 143
abstract_inverted_index.these	110
abstract_inverted_index.users	121
abstract_inverted_index.video	16, 21, 27, 60, 130
abstract_inverted_index.while	91
abstract_inverted_index.wider	147
abstract_inverted_index.across	70, 133
abstract_inverted_index.camera	39, 86, 95, 125
abstract_inverted_index.create	67
abstract_inverted_index.degree	82
abstract_inverted_index.enable	115
abstract_inverted_index.model.	18
abstract_inverted_index.models	23
abstract_inverted_index.module	97
abstract_inverted_index.scenes	52
abstract_inverted_index.scheme	100
abstract_inverted_index.suffer	24
abstract_inverted_index.videos	36
abstract_inverted_index.within	58
abstract_inverted_index.content	57
abstract_inverted_index.dataset	78
abstract_inverted_index.diverse	134
abstract_inverted_index.dynamic	10, 51, 56, 142
abstract_inverted_index.enables	8, 140
abstract_inverted_index.expands	47
abstract_inverted_index.limited	30
abstract_inverted_index.models.	107
abstract_inverted_index.ranges.	73
abstract_inverted_index.spatial	148
abstract_inverted_index.specify	124
abstract_inverted_index.through	13
abstract_inverted_index.Building	108
abstract_inverted_index.Previous	19
abstract_inverted_index.allowing	120
abstract_inverted_index.approach	44
abstract_inverted_index.coherent	129
abstract_inverted_index.dynamics	28, 84, 103
abstract_inverted_index.extended	116
abstract_inverted_index.improved	111
abstract_inverted_index.preserve	102
abstract_inverted_index.previous	151
abstract_inverted_index.seamless	68
abstract_inverted_index.training	90, 99
abstract_inverted_index.construct	76
abstract_inverted_index.designing	92
abstract_inverted_index.diffusion	17
abstract_inverted_index.enhancing	55
abstract_inverted_index.extending	63
abstract_inverted_index.featuring	79
abstract_inverted_index.framework	6
abstract_inverted_index.injection	96
abstract_inverted_index.movement.	40
abstract_inverted_index.parameter	87
abstract_inverted_index.scenarios	135
abstract_inverted_index.synthesis	144
abstract_inverted_index.viewpoint	72
abstract_inverted_index.CameraCtrl	3, 138
abstract_inverted_index.capability	65
abstract_inverted_index.diminished	26
abstract_inverted_index.generating	35, 128
abstract_inverted_index.generation	49
abstract_inverted_index.generative	22
abstract_inverted_index.individual	59
abstract_inverted_index.introduces	2
abstract_inverted_index.pretrained	106
abstract_inverted_index.sequences.	131
abstract_inverted_index.viewpoints	33
abstract_inverted_index.Experiments	132
abstract_inverted_index.annotations	88
abstract_inverted_index.approaches.	152
abstract_inverted_index.demonstrate	136
abstract_inverted_index.exploration	12, 118, 149
abstract_inverted_index.iteratively	123
abstract_inverted_index.large-scale	9
abstract_inverted_index.lightweight	94
abstract_inverted_index.single-clip	112
abstract_inverted_index.techniques,	113
abstract_inverted_index.explorations	69
abstract_inverted_index.trajectories	126
abstract_inverted_index.Specifically,	74
abstract_inverted_index.progressively	46
abstract_inverted_index.substantially	146
abstract_inverted_index.camera-controlled	15, 141
abstract_inverted_index.camera-conditioned	20
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	10
citation_normalized_percentile