Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop Article Swipe

PDF

Zhaofang Qian , Abolfazl Sharifi , T. A. Carroll , Ser-Nam Lim ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.18644

Video generation has achieved impressive quality, but it still suffers from artifacts such as temporal inconsistency and violation of physical laws. Leveraging 3D scenes can fundamentally resolve these issues by providing precise control over scene entities. To facilitate the easy generation of diverse photorealistic scenes, we propose Scene Copilot, a framework combining large language models (LLMs) with a procedural 3D scene generator. Specifically, Scene Copilot consists of Scene Codex, BlenderGPT, and Human in the loop. Scene Codex is designed to translate textual user input into commands understandable by the 3D scene generator. BlenderGPT provides users with an intuitive and direct way to precisely control the generated 3D scene and the final output video. Furthermore, users can utilize Blender UI to receive instant visual feedback. Additionally, we have curated a procedural dataset of objects in code format to further enhance our system's capabilities. Each component works seamlessly together to support users in generating desired 3D scenes. Extensive experiments demonstrate the capability of our framework in customizing 3D scenes and video generation.

Related Topics

Computer Science

Artificial Intelligence

Mathematics

Combinatorics

Concepts

Loop (graph theory) Human-in-the-loop Computer science Procedural modeling Artificial intelligence Mathematics Combinatorics

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2411.18644
PDF: https://arxiv.org/pdf/2411.18644
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4405029422

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405029422

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2411.18644

Digital Object Identifier
Title: Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-11-26

Full publication date if available
Authors: Zhaofang Qian, Abolfazl Sharifi, T. A. Carroll, Ser-Nam Lim

List of authors in order
Landing page: https://arxiv.org/abs/2411.18644

Publisher landing page
PDF URL: https://arxiv.org/pdf/2411.18644

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/2411.18644

Direct OA link when available
Concepts: Loop (graph theory), Human-in-the-loop, Computer science, Procedural modeling, Artificial intelligence, Mathematics, Combinatorics

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/W4405029422
doi	https://doi.org/10.48550/arxiv.2411.18644
ids.doi	https://doi.org/10.48550/arxiv.2411.18644
ids.openalex	https://openalex.org/W4405029422
fwci
type	preprint
title	Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12290
topics[0].field.id	https://openalex.org/fields/22
topics[0].field.display_name	Engineering
topics[0].score	0.9912999868392944
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/2207
topics[0].subfield.display_name	Control and Systems Engineering
topics[0].display_name	Human Motion and Animation
topics[1].id	https://openalex.org/T11439
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9769999980926514
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	Video Analysis and Summarization
topics[2].id	https://openalex.org/T10799
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9351999759674072
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1707
topics[2].subfield.display_name	Computer Vision and Pattern Recognition
topics[2].display_name	Data Visualization and Analytics
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C184670325
concepts[0].level	2
concepts[0].score	0.674686074256897
concepts[0].wikidata	https://www.wikidata.org/wiki/Q512604
concepts[0].display_name	Loop (graph theory)
concepts[1].id	https://openalex.org/C2780626000
concepts[1].level	2
concepts[1].score	0.6091338992118835
concepts[1].wikidata	https://www.wikidata.org/wiki/Q5936775
concepts[1].display_name	Human-in-the-loop
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.5269333124160767
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C113230428
concepts[3].level	2
concepts[3].score	0.48347288370132446
concepts[3].wikidata	https://www.wikidata.org/wiki/Q7247149
concepts[3].display_name	Procedural modeling
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.35451751947402954
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C33923547
concepts[5].level	0
concepts[5].score	0.11681964993476868
concepts[5].wikidata	https://www.wikidata.org/wiki/Q395
concepts[5].display_name	Mathematics
concepts[6].id	https://openalex.org/C114614502
concepts[6].level	1
concepts[6].score	0.0
concepts[6].wikidata	https://www.wikidata.org/wiki/Q76592
concepts[6].display_name	Combinatorics
keywords[0].id	https://openalex.org/keywords/loop
keywords[0].score	0.674686074256897
keywords[0].display_name	Loop (graph theory)
keywords[1].id	https://openalex.org/keywords/human-in-the-loop
keywords[1].score	0.6091338992118835
keywords[1].display_name	Human-in-the-loop
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.5269333124160767
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/procedural-modeling
keywords[3].score	0.48347288370132446
keywords[3].display_name	Procedural modeling
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.35451751947402954
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/mathematics
keywords[5].score	0.11681964993476868
keywords[5].display_name	Mathematics
language	en
locations[0].id	pmh:oai:arXiv.org:2411.18644
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/2411.18644
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/2411.18644
locations[1].id	doi:10.48550/arxiv.2411.18644
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.2411.18644
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5102631929
authorships[0].author.orcid
authorships[0].author.display_name	Zhaofang Qian
authorships[0].author_position	first
authorships[0].raw_author_name	Qian, Zhaofang
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5088634481
authorships[1].author.orcid	https://orcid.org/0000-0002-4957-4481
authorships[1].author.display_name	Abolfazl Sharifi
authorships[1].author_position	middle
authorships[1].raw_author_name	Sharifi, Abolfazl
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5043109896
authorships[2].author.orcid	https://orcid.org/0009-0003-3696-7774
authorships[2].author.display_name	T. A. Carroll
authorships[2].author_position	middle
authorships[2].raw_author_name	Carroll, Tucker
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5113969216
authorships[3].author.orcid	https://orcid.org/0000-0001-9525-0288
authorships[3].author.display_name	Ser-Nam Lim
authorships[3].author_position	last
authorships[3].raw_author_name	Lim, Ser-Nam
authorships[3].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/2411.18644
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-12-05T00:00:00
display_name	Scene Co-pilot: Procedural Text to Video Generation with Human in the Loop
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12290
primary_topic.field.id	https://openalex.org/fields/22
primary_topic.field.display_name	Engineering
primary_topic.score	0.9912999868392944
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2207
primary_topic.subfield.display_name	Control and Systems Engineering
primary_topic.display_name	Human Motion and Animation
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W24774503, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W4288099294, https://openalex.org/W4367173559, https://openalex.org/W4404795748, https://openalex.org/W4404893116
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2411.18644
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/2411.18644
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/2411.18644
primary_location.id	pmh:oai:arXiv.org:2411.18644
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/2411.18644
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/2411.18644
publication_date	2024-11-26
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	49, 57, 128
abstract_inverted_index.3D	22, 59, 89, 106, 153, 165
abstract_inverted_index.To	36
abstract_inverted_index.UI	118
abstract_inverted_index.an	96
abstract_inverted_index.as	13
abstract_inverted_index.by	29, 87
abstract_inverted_index.in	72, 133, 150, 163
abstract_inverted_index.is	77
abstract_inverted_index.it	7
abstract_inverted_index.of	18, 41, 66, 131, 160
abstract_inverted_index.to	79, 101, 119, 136, 147
abstract_inverted_index.we	45, 125
abstract_inverted_index.and	16, 70, 98, 108, 167
abstract_inverted_index.but	6
abstract_inverted_index.can	24, 115
abstract_inverted_index.has	2
abstract_inverted_index.our	139, 161
abstract_inverted_index.the	38, 73, 88, 104, 109, 158
abstract_inverted_index.way	100
abstract_inverted_index.Each	142
abstract_inverted_index.code	134
abstract_inverted_index.easy	39
abstract_inverted_index.from	10
abstract_inverted_index.have	126
abstract_inverted_index.into	84
abstract_inverted_index.over	33
abstract_inverted_index.such	12
abstract_inverted_index.user	82
abstract_inverted_index.with	56, 95
abstract_inverted_index.Codex	76
abstract_inverted_index.Human	71
abstract_inverted_index.Scene	47, 63, 67, 75
abstract_inverted_index.Video	0
abstract_inverted_index.final	110
abstract_inverted_index.input	83
abstract_inverted_index.large	52
abstract_inverted_index.laws.	20
abstract_inverted_index.loop.	74
abstract_inverted_index.scene	34, 60, 90, 107
abstract_inverted_index.still	8
abstract_inverted_index.these	27
abstract_inverted_index.users	94, 114, 149
abstract_inverted_index.video	168
abstract_inverted_index.works	144
abstract_inverted_index.(LLMs)	55
abstract_inverted_index.Codex,	68
abstract_inverted_index.direct	99
abstract_inverted_index.format	135
abstract_inverted_index.issues	28
abstract_inverted_index.models	54
abstract_inverted_index.output	111
abstract_inverted_index.scenes	23, 166
abstract_inverted_index.video.	112
abstract_inverted_index.visual	122
abstract_inverted_index.Blender	117
abstract_inverted_index.Copilot	64
abstract_inverted_index.control	32, 103
abstract_inverted_index.curated	127
abstract_inverted_index.dataset	130
abstract_inverted_index.desired	152
abstract_inverted_index.diverse	42
abstract_inverted_index.enhance	138
abstract_inverted_index.further	137
abstract_inverted_index.instant	121
abstract_inverted_index.objects	132
abstract_inverted_index.precise	31
abstract_inverted_index.propose	46
abstract_inverted_index.receive	120
abstract_inverted_index.resolve	26
abstract_inverted_index.scenes,	44
abstract_inverted_index.scenes.	154
abstract_inverted_index.suffers	9
abstract_inverted_index.support	148
abstract_inverted_index.textual	81
abstract_inverted_index.utilize	116
abstract_inverted_index.Copilot,	48
abstract_inverted_index.achieved	3
abstract_inverted_index.commands	85
abstract_inverted_index.consists	65
abstract_inverted_index.designed	78
abstract_inverted_index.language	53
abstract_inverted_index.physical	19
abstract_inverted_index.provides	93
abstract_inverted_index.quality,	5
abstract_inverted_index.system's	140
abstract_inverted_index.temporal	14
abstract_inverted_index.together	146
abstract_inverted_index.Extensive	155
abstract_inverted_index.artifacts	11
abstract_inverted_index.combining	51
abstract_inverted_index.component	143
abstract_inverted_index.entities.	35
abstract_inverted_index.feedback.	123
abstract_inverted_index.framework	50, 162
abstract_inverted_index.generated	105
abstract_inverted_index.intuitive	97
abstract_inverted_index.precisely	102
abstract_inverted_index.providing	30
abstract_inverted_index.translate	80
abstract_inverted_index.violation	17
abstract_inverted_index.BlenderGPT	92
abstract_inverted_index.Leveraging	21
abstract_inverted_index.capability	159
abstract_inverted_index.facilitate	37
abstract_inverted_index.generating	151
abstract_inverted_index.generation	1, 40
abstract_inverted_index.generator.	61, 91
abstract_inverted_index.impressive	4
abstract_inverted_index.procedural	58, 129
abstract_inverted_index.seamlessly	145
abstract_inverted_index.BlenderGPT,	69
abstract_inverted_index.customizing	164
abstract_inverted_index.demonstrate	157
abstract_inverted_index.experiments	156
abstract_inverted_index.generation.	169
abstract_inverted_index.Furthermore,	113
abstract_inverted_index.Additionally,	124
abstract_inverted_index.Specifically,	62
abstract_inverted_index.capabilities.	141
abstract_inverted_index.fundamentally	25
abstract_inverted_index.inconsistency	15
abstract_inverted_index.photorealistic	43
abstract_inverted_index.understandable	86
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile