GenEx: Generating an Explorable World Article Swipe

PDF

Taiming Lu , Tianmin Shu , Junfei Xiao , Luoxin Ye , Jiahao Wang , Peng Cheng , Wei Chen , Daniel Khashabi , Rama Chellappa , Alan Yuille , Jieneng Chen ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2412.09624

Understanding, navigating, and exploring the 3D physical real world has long been a central challenge in the development of artificial intelligence. In this work, we take a step toward this goal by introducing GenEx, a system capable of planning complex embodied world exploration, guided by its generative imagination that forms priors (expectations) about the surrounding environments. GenEx generates an entire 3D-consistent imaginative environment from as little as a single RGB image, bringing it to life through panoramic video streams. Leveraging scalable 3D world data curated from Unreal Engine, our generative model is rounded in the physical world. It captures a continuous 360-degree environment with little effort, offering a boundless landscape for AI agents to explore and interact with. GenEx achieves high-quality world generation, robust loop consistency over long trajectories, and demonstrates strong 3D capabilities such as consistency and active 3D mapping. Powered by generative imagination of the world, GPT-assisted agents are equipped to perform complex embodied tasks, including both goal-agnostic exploration and goal-driven navigation. These agents utilize predictive expectation regarding unseen parts of the physical world to refine their beliefs, simulate different outcomes based on potential decisions, and make more informed choices. In summary, we demonstrate that GenEx provides a transformative platform for advancing embodied AI in imaginative spaces and brings potential for extending these capabilities to real-world exploration.

Related Topics

Computer Science

Concepts

Computer science

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2412.09624
PDF: https://arxiv.org/pdf/2412.09624
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4405355508

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4405355508

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2412.09624

Digital Object Identifier
Title: GenEx: Generating an Explorable World

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-12-12

Full publication date if available
Authors: Taiming Lu, Tianmin Shu, Junfei Xiao, Luoxin Ye, Jiahao Wang, Peng Cheng, Wei Chen, Daniel Khashabi, Rama Chellappa, Alan Yuille, Jieneng Chen

List of authors in order
Landing page: https://arxiv.org/abs/2412.09624

Publisher landing page
PDF URL: https://arxiv.org/pdf/2412.09624

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/2412.09624

Direct OA link when available
Concepts: Computer science

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/W4405355508
doi	https://doi.org/10.48550/arxiv.2412.09624
ids.doi	https://doi.org/10.48550/arxiv.2412.09624
ids.openalex	https://openalex.org/W4405355508
fwci
type	preprint
title	GenEx: Generating an Explorable World
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.47990262508392334
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.47990262508392334
keywords[0].display_name	Computer science
language	en
locations[0].id	pmh:oai:arXiv.org:2412.09624
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/2412.09624
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/2412.09624
locations[1].id	doi:10.48550/arxiv.2412.09624
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.2412.09624
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5099446810
authorships[0].author.orcid
authorships[0].author.display_name	Taiming Lu
authorships[0].author_position	first
authorships[0].raw_author_name	Lu, Taiming
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5005908625
authorships[1].author.orcid
authorships[1].author.display_name	Tianmin Shu
authorships[1].author_position	middle
authorships[1].raw_author_name	Shu, Tianmin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5016734799
authorships[2].author.orcid
authorships[2].author.display_name	Junfei Xiao
authorships[2].author_position	middle
authorships[2].raw_author_name	Xiao, Junfei
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5113273834
authorships[3].author.orcid
authorships[3].author.display_name	Luoxin Ye
authorships[3].author_position	middle
authorships[3].raw_author_name	Ye, Luoxin
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5070072724
authorships[4].author.orcid	https://orcid.org/0009-0002-5591-3520
authorships[4].author.display_name	Jiahao Wang
authorships[4].author_position	middle
authorships[4].raw_author_name	Wang, Jiahao
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5012637338
authorships[5].author.orcid	https://orcid.org/0000-0003-2351-2060
authorships[5].author.display_name	Peng Cheng
authorships[5].author_position	middle
authorships[5].raw_author_name	Peng, Cheng
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5100344395
authorships[6].author.orcid	https://orcid.org/0000-0002-1919-594X
authorships[6].author.display_name	Wei Chen
authorships[6].author_position	middle
authorships[6].raw_author_name	Wei, Chen
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5043628255
authorships[7].author.orcid	https://orcid.org/0009-0009-7664-2230
authorships[7].author.display_name	Daniel Khashabi
authorships[7].author_position	middle
authorships[7].raw_author_name	Khashabi, Daniel
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5102762707
authorships[8].author.orcid	https://orcid.org/0000-0002-7638-1650
authorships[8].author.display_name	Rama Chellappa
authorships[8].author_position	middle
authorships[8].raw_author_name	Chellappa, Rama
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5086706224
authorships[9].author.orcid	https://orcid.org/0000-0001-5207-9249
authorships[9].author.display_name	Alan Yuille
authorships[9].author_position	middle
authorships[9].raw_author_name	Yuille, Alan
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5066600512
authorships[10].author.orcid	https://orcid.org/0000-0002-6692-4455
authorships[10].author.display_name	Jieneng Chen
authorships[10].author_position	last
authorships[10].raw_author_name	Chen, Jieneng
authorships[10].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/2412.09624
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	GenEx: Generating an Explorable World
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2412.09624
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/2412.09624
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/2412.09624
primary_location.id	pmh:oai:arXiv.org:2412.09624
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/2412.09624
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/2412.09624
publication_date	2024-12-12
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	12, 26, 34, 67, 99, 107, 199
abstract_inverted_index.3D	5, 81, 132, 139
abstract_inverted_index.AI	111, 205
abstract_inverted_index.In	21, 192
abstract_inverted_index.It	97
abstract_inverted_index.an	58
abstract_inverted_index.as	64, 66, 135
abstract_inverted_index.by	31, 44, 142
abstract_inverted_index.in	15, 93, 206
abstract_inverted_index.is	91
abstract_inverted_index.it	72
abstract_inverted_index.of	18, 37, 145, 172
abstract_inverted_index.on	184
abstract_inverted_index.to	73, 113, 152, 176, 216
abstract_inverted_index.we	24, 194
abstract_inverted_index.RGB	69
abstract_inverted_index.and	2, 115, 129, 137, 161, 187, 209
abstract_inverted_index.are	150
abstract_inverted_index.for	110, 202, 212
abstract_inverted_index.has	9
abstract_inverted_index.its	45
abstract_inverted_index.our	88
abstract_inverted_index.the	4, 16, 53, 94, 146, 173
abstract_inverted_index.been	11
abstract_inverted_index.both	158
abstract_inverted_index.data	83
abstract_inverted_index.from	63, 85
abstract_inverted_index.goal	30
abstract_inverted_index.life	74
abstract_inverted_index.long	10, 127
abstract_inverted_index.loop	124
abstract_inverted_index.make	188
abstract_inverted_index.more	189
abstract_inverted_index.over	126
abstract_inverted_index.real	7
abstract_inverted_index.step	27
abstract_inverted_index.such	134
abstract_inverted_index.take	25
abstract_inverted_index.that	48, 196
abstract_inverted_index.this	22, 29
abstract_inverted_index.with	103
abstract_inverted_index.GenEx	56, 118, 197
abstract_inverted_index.These	164
abstract_inverted_index.about	52
abstract_inverted_index.based	183
abstract_inverted_index.forms	49
abstract_inverted_index.model	90
abstract_inverted_index.parts	171
abstract_inverted_index.their	178
abstract_inverted_index.these	214
abstract_inverted_index.video	77
abstract_inverted_index.with.	117
abstract_inverted_index.work,	23
abstract_inverted_index.world	8, 41, 82, 121, 175
abstract_inverted_index.GenEx,	33
abstract_inverted_index.Unreal	86
abstract_inverted_index.active	138
abstract_inverted_index.agents	112, 149, 165
abstract_inverted_index.brings	210
abstract_inverted_index.entire	59
abstract_inverted_index.guided	43
abstract_inverted_index.image,	70
abstract_inverted_index.little	65, 104
abstract_inverted_index.priors	50
abstract_inverted_index.refine	177
abstract_inverted_index.robust	123
abstract_inverted_index.single	68
abstract_inverted_index.spaces	208
abstract_inverted_index.strong	131
abstract_inverted_index.system	35
abstract_inverted_index.tasks,	156
abstract_inverted_index.toward	28
abstract_inverted_index.unseen	170
abstract_inverted_index.world,	147
abstract_inverted_index.world.	96
abstract_inverted_index.Engine,	87
abstract_inverted_index.Powered	141
abstract_inverted_index.capable	36
abstract_inverted_index.central	13
abstract_inverted_index.complex	39, 154
abstract_inverted_index.curated	84
abstract_inverted_index.effort,	105
abstract_inverted_index.explore	114
abstract_inverted_index.perform	153
abstract_inverted_index.rounded	92
abstract_inverted_index.through	75
abstract_inverted_index.utilize	166
abstract_inverted_index.achieves	119
abstract_inverted_index.beliefs,	179
abstract_inverted_index.bringing	71
abstract_inverted_index.captures	98
abstract_inverted_index.choices.	191
abstract_inverted_index.embodied	40, 155, 204
abstract_inverted_index.equipped	151
abstract_inverted_index.informed	190
abstract_inverted_index.interact	116
abstract_inverted_index.mapping.	140
abstract_inverted_index.offering	106
abstract_inverted_index.outcomes	182
abstract_inverted_index.physical	6, 95, 174
abstract_inverted_index.planning	38
abstract_inverted_index.platform	201
abstract_inverted_index.provides	198
abstract_inverted_index.scalable	80
abstract_inverted_index.simulate	180
abstract_inverted_index.streams.	78
abstract_inverted_index.summary,	193
abstract_inverted_index.advancing	203
abstract_inverted_index.boundless	108
abstract_inverted_index.challenge	14
abstract_inverted_index.different	181
abstract_inverted_index.exploring	3
abstract_inverted_index.extending	213
abstract_inverted_index.generates	57
abstract_inverted_index.including	157
abstract_inverted_index.landscape	109
abstract_inverted_index.panoramic	76
abstract_inverted_index.potential	185, 211
abstract_inverted_index.regarding	169
abstract_inverted_index.360-degree	101
abstract_inverted_index.Leveraging	79
abstract_inverted_index.artificial	19
abstract_inverted_index.continuous	100
abstract_inverted_index.decisions,	186
abstract_inverted_index.generative	46, 89, 143
abstract_inverted_index.predictive	167
abstract_inverted_index.real-world	217
abstract_inverted_index.consistency	125, 136
abstract_inverted_index.demonstrate	195
abstract_inverted_index.development	17
abstract_inverted_index.environment	62, 102
abstract_inverted_index.expectation	168
abstract_inverted_index.exploration	160
abstract_inverted_index.generation,	122
abstract_inverted_index.goal-driven	162
abstract_inverted_index.imagination	47, 144
abstract_inverted_index.imaginative	61, 207
abstract_inverted_index.introducing	32
abstract_inverted_index.navigating,	1
abstract_inverted_index.navigation.	163
abstract_inverted_index.surrounding	54
abstract_inverted_index.GPT-assisted	148
abstract_inverted_index.capabilities	133, 215
abstract_inverted_index.demonstrates	130
abstract_inverted_index.exploration,	42
abstract_inverted_index.exploration.	218
abstract_inverted_index.high-quality	120
abstract_inverted_index.3D-consistent	60
abstract_inverted_index.environments.	55
abstract_inverted_index.goal-agnostic	159
abstract_inverted_index.intelligence.	20
abstract_inverted_index.trajectories,	128
abstract_inverted_index.(expectations)	51
abstract_inverted_index.Understanding,	0
abstract_inverted_index.transformative	200
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	11
citation_normalized_percentile