IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation Article Swipe
Yizhi Song
,
Zhifei Zhang
,
Zhe Lin
,
Scott Cohen
,
Brian Price
,
Jianming Zhang
,
Soo Ye Kim
,
He Zhang
,
Wei Xiong
,
Daniel G. Aliaga
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.10701
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.10701
Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In response, this paper introduces IMPRINT, a novel diffusion-based generative model trained with a two-stage learning framework that decouples learning of identity preservation from that of compositing. The first stage is targeted for context-agnostic, identity-preserving pretraining of the object encoder, enabling the encoder to learn an embedding that is both view-invariant and conducive to enhanced detail preservation. The subsequent stage leverages this representation to learn seamless harmonization of the object composited to the background. In addition, IMPRINT incorporates a shape-guidance mechanism offering user-directed control over the compositing process. Extensive experiments demonstrate that IMPRINT significantly outperforms existing methods and various baselines on identity preservation and composition quality.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.10701
- https://arxiv.org/pdf/2403.10701
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392971969
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392971969Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.10701Digital Object Identifier
- Title
-
IMPRINT: Generative Object Compositing by Learning Identity-Preserving RepresentationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-15Full publication date if available
- Authors
-
Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel G. AliagaList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.10701Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.10701Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2403.10701Direct OA link when available
- Concepts
-
Compositing, Representation (politics), Generative grammar, Object (grammar), Identity (music), Computer science, Generative model, Artificial intelligence, Image (mathematics), Aesthetics, Art, Political science, Politics, LawTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392971969 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.10701 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.10701 |
| ids.openalex | https://openalex.org/W4392971969 |
| fwci | |
| type | preprint |
| title | IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12002 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.79339998960495 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1703 |
| topics[0].subfield.display_name | Computational Theory and Mathematics |
| topics[0].display_name | Computability, Logic, AI Algorithms |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C129315195 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8091868162155151 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1121886 |
| concepts[0].display_name | Compositing |
| concepts[1].id | https://openalex.org/C2776359362 |
| concepts[1].level | 3 |
| concepts[1].score | 0.7258076667785645 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[1].display_name | Representation (politics) |
| concepts[2].id | https://openalex.org/C39890363 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6979511976242065 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q36108 |
| concepts[2].display_name | Generative grammar |
| concepts[3].id | https://openalex.org/C2781238097 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6260915398597717 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q175026 |
| concepts[3].display_name | Object (grammar) |
| concepts[4].id | https://openalex.org/C2778355321 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6132071614265442 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q17079427 |
| concepts[4].display_name | Identity (music) |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.4758598208427429 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C167966045 |
| concepts[6].level | 3 |
| concepts[6].score | 0.4641289710998535 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q5532625 |
| concepts[6].display_name | Generative model |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4401942789554596 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C115961682 |
| concepts[8].level | 2 |
| concepts[8].score | 0.22985684871673584 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[8].display_name | Image (mathematics) |
| concepts[9].id | https://openalex.org/C107038049 |
| concepts[9].level | 1 |
| concepts[9].score | 0.18269279599189758 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q35986 |
| concepts[9].display_name | Aesthetics |
| concepts[10].id | https://openalex.org/C142362112 |
| concepts[10].level | 0 |
| concepts[10].score | 0.15396040678024292 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q735 |
| concepts[10].display_name | Art |
| concepts[11].id | https://openalex.org/C17744445 |
| concepts[11].level | 0 |
| concepts[11].score | 0.10840842127799988 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[11].display_name | Political science |
| concepts[12].id | https://openalex.org/C94625758 |
| concepts[12].level | 2 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[12].display_name | Politics |
| concepts[13].id | https://openalex.org/C199539241 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[13].display_name | Law |
| keywords[0].id | https://openalex.org/keywords/compositing |
| keywords[0].score | 0.8091868162155151 |
| keywords[0].display_name | Compositing |
| keywords[1].id | https://openalex.org/keywords/representation |
| keywords[1].score | 0.7258076667785645 |
| keywords[1].display_name | Representation (politics) |
| keywords[2].id | https://openalex.org/keywords/generative-grammar |
| keywords[2].score | 0.6979511976242065 |
| keywords[2].display_name | Generative grammar |
| keywords[3].id | https://openalex.org/keywords/object |
| keywords[3].score | 0.6260915398597717 |
| keywords[3].display_name | Object (grammar) |
| keywords[4].id | https://openalex.org/keywords/identity |
| keywords[4].score | 0.6132071614265442 |
| keywords[4].display_name | Identity (music) |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.4758598208427429 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/generative-model |
| keywords[6].score | 0.4641289710998535 |
| keywords[6].display_name | Generative model |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.4401942789554596 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/image |
| keywords[8].score | 0.22985684871673584 |
| keywords[8].display_name | Image (mathematics) |
| keywords[9].id | https://openalex.org/keywords/aesthetics |
| keywords[9].score | 0.18269279599189758 |
| keywords[9].display_name | Aesthetics |
| keywords[10].id | https://openalex.org/keywords/art |
| keywords[10].score | 0.15396040678024292 |
| keywords[10].display_name | Art |
| keywords[11].id | https://openalex.org/keywords/political-science |
| keywords[11].score | 0.10840842127799988 |
| keywords[11].display_name | Political science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.10701 |
| 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 | cc-by-nc-nd |
| locations[0].pdf_url | https://arxiv.org/pdf/2403.10701 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2403.10701 |
| locations[1].id | doi:10.48550/arxiv.2403.10701 |
| 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.2403.10701 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101019993 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yizhi Song |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Song, Yizhi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100626853 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4399-2356 |
| authorships[1].author.display_name | Zhifei Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Zhifei |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101564904 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1154-9907 |
| authorships[2].author.display_name | Zhe Lin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lin, Zhe |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5055156362 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-3459-6899 |
| authorships[3].author.display_name | Scott Cohen |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Cohen, Scott |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5110699179 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Brian Price |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Price, Brian |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100427565 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4278-0805 |
| authorships[5].author.display_name | Jianming Zhang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhang, Jianming |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5016563944 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Soo Ye Kim |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Kim, Soo Ye |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5100519515 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | He Zhang |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Zhang, He |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5100622634 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-0099-6050 |
| authorships[8].author.display_name | Wei Xiong |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Xiong, Wei |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5090414723 |
| authorships[9].author.orcid | https://orcid.org/0000-0001-9794-462X |
| authorships[9].author.display_name | Daniel G. Aliaga |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Aliaga, Daniel |
| authorships[9].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2403.10701 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-03-20T00:00:00 |
| display_name | IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12002 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.79339998960495 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1703 |
| primary_topic.subfield.display_name | Computational Theory and Mathematics |
| primary_topic.display_name | Computability, Logic, AI Algorithms |
| related_works | https://openalex.org/W4365211920, https://openalex.org/W3014948380, https://openalex.org/W1834370135, https://openalex.org/W4380551139, https://openalex.org/W4317695495, https://openalex.org/W2280377497, https://openalex.org/W4387506531, https://openalex.org/W4238433571, https://openalex.org/W3174044702, https://openalex.org/W2967848559 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.10701 |
| 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 | cc-by-nc-nd |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2403.10701 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| 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/2403.10701 |
| primary_location.id | pmh:oai:arXiv.org:2403.10701 |
| 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 | cc-by-nc-nd |
| primary_location.pdf_url | https://arxiv.org/pdf/2403.10701 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2403.10701 |
| publication_date | 2024-03-15 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 5, 21, 37, 44, 109 |
| abstract_inverted_index.In | 31, 105 |
| abstract_inverted_index.an | 76 |
| abstract_inverted_index.as | 4 |
| abstract_inverted_index.is | 61, 79 |
| abstract_inverted_index.of | 16, 27, 51, 56, 67, 98 |
| abstract_inverted_index.on | 131 |
| abstract_inverted_index.to | 74, 84, 94, 102 |
| abstract_inverted_index.The | 58, 88 |
| abstract_inverted_index.and | 82, 128, 134 |
| abstract_inverted_index.for | 9, 63 |
| abstract_inverted_index.new | 7 |
| abstract_inverted_index.the | 14, 68, 72, 99, 103, 116 |
| abstract_inverted_index.both | 80 |
| abstract_inverted_index.from | 54 |
| abstract_inverted_index.most | 28 |
| abstract_inverted_index.over | 115 |
| abstract_inverted_index.that | 48, 55, 78, 122 |
| abstract_inverted_index.this | 33, 92 |
| abstract_inverted_index.with | 43 |
| abstract_inverted_index.first | 59 |
| abstract_inverted_index.image | 11 |
| abstract_inverted_index.learn | 75, 95 |
| abstract_inverted_index.model | 41 |
| abstract_inverted_index.novel | 38 |
| abstract_inverted_index.paper | 34 |
| abstract_inverted_index.poses | 20 |
| abstract_inverted_index.stage | 60, 90 |
| abstract_inverted_index.usage | 26 |
| abstract_inverted_index.avenue | 8 |
| abstract_inverted_index.detail | 86 |
| abstract_inverted_index.object | 1, 17, 69, 100 |
| abstract_inverted_index.IMPRINT | 107, 123 |
| abstract_inverted_index.control | 114 |
| abstract_inverted_index.emerges | 3 |
| abstract_inverted_index.encoder | 73 |
| abstract_inverted_index.methods | 127 |
| abstract_inverted_index.trained | 42 |
| abstract_inverted_index.various | 129 |
| abstract_inverted_index.However, | 13 |
| abstract_inverted_index.IMPRINT, | 36 |
| abstract_inverted_index.editing. | 12 |
| abstract_inverted_index.enabling | 71 |
| abstract_inverted_index.encoder, | 70 |
| abstract_inverted_index.enhanced | 85 |
| abstract_inverted_index.existing | 29, 126 |
| abstract_inverted_index.identity | 18, 52, 132 |
| abstract_inverted_index.learning | 46, 50 |
| abstract_inverted_index.limiting | 24 |
| abstract_inverted_index.methods. | 30 |
| abstract_inverted_index.offering | 112 |
| abstract_inverted_index.process. | 118 |
| abstract_inverted_index.quality. | 136 |
| abstract_inverted_index.seamless | 96 |
| abstract_inverted_index.targeted | 62 |
| abstract_inverted_index.Extensive | 119 |
| abstract_inverted_index.addition, | 106 |
| abstract_inverted_index.baselines | 130 |
| abstract_inverted_index.conducive | 83 |
| abstract_inverted_index.decouples | 49 |
| abstract_inverted_index.embedding | 77 |
| abstract_inverted_index.framework | 47 |
| abstract_inverted_index.leverages | 91 |
| abstract_inverted_index.mechanism | 111 |
| abstract_inverted_index.practical | 25 |
| abstract_inverted_index.promising | 6 |
| abstract_inverted_index.response, | 32 |
| abstract_inverted_index.two-stage | 45 |
| abstract_inverted_index.Generative | 0 |
| abstract_inverted_index.challenge, | 23 |
| abstract_inverted_index.composited | 101 |
| abstract_inverted_index.generative | 40 |
| abstract_inverted_index.introduces | 35 |
| abstract_inverted_index.subsequent | 89 |
| abstract_inverted_index.background. | 104 |
| abstract_inverted_index.compositing | 2, 117 |
| abstract_inverted_index.composition | 135 |
| abstract_inverted_index.demonstrate | 121 |
| abstract_inverted_index.experiments | 120 |
| abstract_inverted_index.outperforms | 125 |
| abstract_inverted_index.pretraining | 66 |
| abstract_inverted_index.requirement | 15 |
| abstract_inverted_index.significant | 22 |
| abstract_inverted_index.compositing. | 57 |
| abstract_inverted_index.incorporates | 108 |
| abstract_inverted_index.preservation | 19, 53, 133 |
| abstract_inverted_index.compositional | 10 |
| abstract_inverted_index.harmonization | 97 |
| abstract_inverted_index.preservation. | 87 |
| abstract_inverted_index.significantly | 124 |
| abstract_inverted_index.user-directed | 113 |
| abstract_inverted_index.representation | 93 |
| abstract_inverted_index.shape-guidance | 110 |
| abstract_inverted_index.view-invariant | 81 |
| abstract_inverted_index.diffusion-based | 39 |
| abstract_inverted_index.context-agnostic, | 64 |
| abstract_inverted_index.identity-preserving | 65 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile |