LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising Article Swipe
Muhammad Waseem
,
Muhammad Usman Ghani Khan
,
Syed Khaldoon Khurshid
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/access.2025.3550945
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1109/access.2025.3550945
Diffusion models have emerged as a leading solution in computer vision and they excel at audio, image, and video generation by utilizing the Markov chain to map complex latent spaces. These models outperform other generative models such as GANs and VAEs, with their noising and denoising processes modeled after U-Net architecture, enabling high-quality text-to-image and text-to-video synthesis. However, existing research has largely focused on application rather than improving underlying architectures, leading to limitations, such as oversmoothing in approaches like FreeU. To address these gaps, we introduce LLM Contextual Guided Diffusion (LCGD), which integrates large language models (LLMs) into the noising and denoising phases to enhance semantic understanding, noise modulation, and feature selection. This approach improves the output realism and coherence, as demonstrated by our results, where SD+LCGD achieved 89.91% compared to 85.88% for SD+FreeU.
Related Topics
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/access.2025.3550945
- OA Status
- gold
- References
- 54
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4408468177
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4408468177Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/access.2025.3550945Digital Object Identifier
- Title
-
LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net DenoisingWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-01Full publication date if available
- Authors
-
Muhammad Waseem, Muhammad Usman Ghani Khan, Syed Khaldoon KhurshidList of authors in order
- Landing page
-
https://doi.org/10.1109/access.2025.3550945Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1109/access.2025.3550945Direct OA link when available
- Concepts
-
Computer science, Noise reduction, Multimedia, Artificial intelligence, Image denoisingTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
54Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4408468177 |
|---|---|
| doi | https://doi.org/10.1109/access.2025.3550945 |
| ids.doi | https://doi.org/10.1109/access.2025.3550945 |
| ids.openalex | https://openalex.org/W4408468177 |
| fwci | 0.0 |
| type | article |
| title | LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising |
| biblio.issue | |
| biblio.volume | 13 |
| biblio.last_page | 47085 |
| biblio.first_page | 47068 |
| topics[0].id | https://openalex.org/T11439 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9714999794960022 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Video Analysis and Summarization |
| is_xpac | False |
| apc_list.value | 1850 |
| apc_list.currency | USD |
| apc_list.value_usd | 1850 |
| apc_paid.value | 1850 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 1850 |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7523878812789917 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C163294075 |
| concepts[1].level | 2 |
| concepts[1].score | 0.525652289390564 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q581861 |
| concepts[1].display_name | Noise reduction |
| concepts[2].id | https://openalex.org/C49774154 |
| concepts[2].level | 1 |
| concepts[2].score | 0.48674988746643066 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q131765 |
| concepts[2].display_name | Multimedia |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.41450372338294983 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C2983327147 |
| concepts[4].level | 3 |
| concepts[4].score | 0.41226300597190857 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q581861 |
| concepts[4].display_name | Image denoising |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7523878812789917 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/noise-reduction |
| keywords[1].score | 0.525652289390564 |
| keywords[1].display_name | Noise reduction |
| keywords[2].id | https://openalex.org/keywords/multimedia |
| keywords[2].score | 0.48674988746643066 |
| keywords[2].display_name | Multimedia |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.41450372338294983 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/image-denoising |
| keywords[4].score | 0.41226300597190857 |
| keywords[4].display_name | Image denoising |
| language | en |
| locations[0].id | doi:10.1109/access.2025.3550945 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S2485537415 |
| locations[0].source.issn | 2169-3536 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 2169-3536 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | IEEE Access |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| locations[0].license | cc-by |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Access |
| locations[0].landing_page_url | https://doi.org/10.1109/access.2025.3550945 |
| locations[1].id | pmh:oai:doaj.org/article:1bdac88e1f804f0abbe926b46118eaf6 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306401280 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | DOAJ (DOAJ: Directory of Open Access Journals) |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | submittedVersion |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | IEEE Access, Vol 13, Pp 47068-47085 (2025) |
| locations[1].landing_page_url | https://doaj.org/article/1bdac88e1f804f0abbe926b46118eaf6 |
| indexed_in | crossref, doaj |
| authorships[0].author.id | https://openalex.org/A5101868241 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9605-2531 |
| authorships[0].author.display_name | Muhammad Waseem |
| authorships[0].countries | PK |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I142732210 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Engineering and Technology, Lahore, Pakistan |
| authorships[0].institutions[0].id | https://openalex.org/I142732210 |
| authorships[0].institutions[0].ror | https://ror.org/0051w2v06 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I142732210 |
| authorships[0].institutions[0].country_code | PK |
| authorships[0].institutions[0].display_name | University of Engineering and Technology Lahore |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Muhammad Waseem |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Engineering and Technology, Lahore, Pakistan |
| authorships[1].author.id | https://openalex.org/A5007976764 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6733-2569 |
| authorships[1].author.display_name | Muhammad Usman Ghani Khan |
| authorships[1].countries | PK |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I142732210 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Engineering and Technology, Lahore, Pakistan |
| authorships[1].institutions[0].id | https://openalex.org/I142732210 |
| authorships[1].institutions[0].ror | https://ror.org/0051w2v06 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I142732210 |
| authorships[1].institutions[0].country_code | PK |
| authorships[1].institutions[0].display_name | University of Engineering and Technology Lahore |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Muhammad Usman Ghani Khan |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Engineering and Technology, Lahore, Pakistan |
| authorships[2].author.id | https://openalex.org/A5051481734 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1818-9115 |
| authorships[2].author.display_name | Syed Khaldoon Khurshid |
| authorships[2].countries | PK |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I142732210 |
| authorships[2].affiliations[0].raw_affiliation_string | University of Engineering and Technology, Lahore, Pakistan |
| authorships[2].institutions[0].id | https://openalex.org/I142732210 |
| authorships[2].institutions[0].ror | https://ror.org/0051w2v06 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I142732210 |
| authorships[2].institutions[0].country_code | PK |
| authorships[2].institutions[0].display_name | University of Engineering and Technology Lahore |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Syed Khaldoon Khurshid |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | University of Engineering and Technology, Lahore, Pakistan |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1109/access.2025.3550945 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | LCGD: Enhancing Text-to-Video Generation via Contextual LLM Guidance and U-Net Denoising |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T11439 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9714999794960022 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Video Analysis and Summarization |
| related_works | https://openalex.org/W2087258800, https://openalex.org/W2810018092, https://openalex.org/W4407169614, https://openalex.org/W2387428419, https://openalex.org/W4401571043, https://openalex.org/W2098237619, https://openalex.org/W1974034585, https://openalex.org/W4406054402, https://openalex.org/W4312627788, https://openalex.org/W2353444452 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1109/access.2025.3550945 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S2485537415 |
| best_oa_location.source.issn | 2169-3536 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 2169-3536 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | IEEE Access |
| best_oa_location.source.host_organization | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | IEEE Access |
| best_oa_location.landing_page_url | https://doi.org/10.1109/access.2025.3550945 |
| primary_location.id | doi:10.1109/access.2025.3550945 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S2485537415 |
| primary_location.source.issn | 2169-3536 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 2169-3536 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | IEEE Access |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| primary_location.license | cc-by |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Access |
| primary_location.landing_page_url | https://doi.org/10.1109/access.2025.3550945 |
| publication_date | 2025-01-01 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W6841755765, https://openalex.org/W6795288823, https://openalex.org/W6840155194, https://openalex.org/W6810793953, https://openalex.org/W4402727849, https://openalex.org/W4402753769, https://openalex.org/W6852849417, https://openalex.org/W6872792134, https://openalex.org/W4402716152, https://openalex.org/W6678815747, https://openalex.org/W3180355996, https://openalex.org/W4311415873, https://openalex.org/W4388854249, https://openalex.org/W4386071957, https://openalex.org/W6838785959, https://openalex.org/W6856700853, https://openalex.org/W6779823529, https://openalex.org/W6809885388, https://openalex.org/W3155072588, https://openalex.org/W6804122398, https://openalex.org/W3172355168, https://openalex.org/W2086363107, https://openalex.org/W4388185854, https://openalex.org/W6861477695, https://openalex.org/W4402715897, https://openalex.org/W6852922754, https://openalex.org/W4402733577, https://openalex.org/W6838461927, https://openalex.org/W6845281891, https://openalex.org/W4402753507, https://openalex.org/W6859952777, https://openalex.org/W4390889802, https://openalex.org/W4312933868, https://openalex.org/W4387596573, https://openalex.org/W6862078622, https://openalex.org/W4389252578, https://openalex.org/W4283275522, https://openalex.org/W6853089504, https://openalex.org/W4405172837, https://openalex.org/W4399575711, https://openalex.org/W4404628801, https://openalex.org/W4387801836, https://openalex.org/W2911590702, https://openalex.org/W3041874265, https://openalex.org/W6860286204, https://openalex.org/W2963032538, https://openalex.org/W1995713768, https://openalex.org/W4402351164, https://openalex.org/W2512630954, https://openalex.org/W4390873767, https://openalex.org/W6790690058, https://openalex.org/W6670595800, https://openalex.org/W4385800720, https://openalex.org/W4388756695 |
| referenced_works_count | 54 |
| abstract_inverted_index.a | 5 |
| abstract_inverted_index.To | 80 |
| abstract_inverted_index.as | 4, 37, 74, 120 |
| abstract_inverted_index.at | 14 |
| abstract_inverted_index.by | 20, 122 |
| abstract_inverted_index.in | 8, 76 |
| abstract_inverted_index.on | 63 |
| abstract_inverted_index.to | 25, 71, 103, 130 |
| abstract_inverted_index.we | 84 |
| abstract_inverted_index.LLM | 86 |
| abstract_inverted_index.and | 11, 17, 39, 44, 54, 100, 109, 118 |
| abstract_inverted_index.for | 132 |
| abstract_inverted_index.has | 60 |
| abstract_inverted_index.map | 26 |
| abstract_inverted_index.our | 123 |
| abstract_inverted_index.the | 22, 98, 115 |
| abstract_inverted_index.GANs | 38 |
| abstract_inverted_index.This | 112 |
| abstract_inverted_index.have | 2 |
| abstract_inverted_index.into | 97 |
| abstract_inverted_index.like | 78 |
| abstract_inverted_index.such | 36, 73 |
| abstract_inverted_index.than | 66 |
| abstract_inverted_index.they | 12 |
| abstract_inverted_index.with | 41 |
| abstract_inverted_index.These | 30 |
| abstract_inverted_index.U-Net | 49 |
| abstract_inverted_index.VAEs, | 40 |
| abstract_inverted_index.after | 48 |
| abstract_inverted_index.chain | 24 |
| abstract_inverted_index.excel | 13 |
| abstract_inverted_index.gaps, | 83 |
| abstract_inverted_index.large | 93 |
| abstract_inverted_index.noise | 107 |
| abstract_inverted_index.other | 33 |
| abstract_inverted_index.their | 42 |
| abstract_inverted_index.these | 82 |
| abstract_inverted_index.video | 18 |
| abstract_inverted_index.where | 125 |
| abstract_inverted_index.which | 91 |
| abstract_inverted_index.(LLMs) | 96 |
| abstract_inverted_index.85.88% | 131 |
| abstract_inverted_index.89.91% | 128 |
| abstract_inverted_index.FreeU. | 79 |
| abstract_inverted_index.Guided | 88 |
| abstract_inverted_index.Markov | 23 |
| abstract_inverted_index.audio, | 15 |
| abstract_inverted_index.image, | 16 |
| abstract_inverted_index.latent | 28 |
| abstract_inverted_index.models | 1, 31, 35, 95 |
| abstract_inverted_index.output | 116 |
| abstract_inverted_index.phases | 102 |
| abstract_inverted_index.rather | 65 |
| abstract_inverted_index.vision | 10 |
| abstract_inverted_index.(LCGD), | 90 |
| abstract_inverted_index.SD+LCGD | 126 |
| abstract_inverted_index.address | 81 |
| abstract_inverted_index.complex | 27 |
| abstract_inverted_index.emerged | 3 |
| abstract_inverted_index.enhance | 104 |
| abstract_inverted_index.feature | 110 |
| abstract_inverted_index.focused | 62 |
| abstract_inverted_index.largely | 61 |
| abstract_inverted_index.leading | 6, 70 |
| abstract_inverted_index.modeled | 47 |
| abstract_inverted_index.noising | 43, 99 |
| abstract_inverted_index.realism | 117 |
| abstract_inverted_index.spaces. | 29 |
| abstract_inverted_index.However, | 57 |
| abstract_inverted_index.achieved | 127 |
| abstract_inverted_index.approach | 113 |
| abstract_inverted_index.compared | 129 |
| abstract_inverted_index.computer | 9 |
| abstract_inverted_index.enabling | 51 |
| abstract_inverted_index.existing | 58 |
| abstract_inverted_index.improves | 114 |
| abstract_inverted_index.language | 94 |
| abstract_inverted_index.research | 59 |
| abstract_inverted_index.results, | 124 |
| abstract_inverted_index.semantic | 105 |
| abstract_inverted_index.solution | 7 |
| abstract_inverted_index.Diffusion | 0, 89 |
| abstract_inverted_index.SD+FreeU. | 133 |
| abstract_inverted_index.denoising | 45, 101 |
| abstract_inverted_index.improving | 67 |
| abstract_inverted_index.introduce | 85 |
| abstract_inverted_index.processes | 46 |
| abstract_inverted_index.utilizing | 21 |
| abstract_inverted_index.Contextual | 87 |
| abstract_inverted_index.approaches | 77 |
| abstract_inverted_index.coherence, | 119 |
| abstract_inverted_index.generation | 19 |
| abstract_inverted_index.generative | 34 |
| abstract_inverted_index.integrates | 92 |
| abstract_inverted_index.outperform | 32 |
| abstract_inverted_index.selection. | 111 |
| abstract_inverted_index.synthesis. | 56 |
| abstract_inverted_index.underlying | 68 |
| abstract_inverted_index.application | 64 |
| abstract_inverted_index.modulation, | 108 |
| abstract_inverted_index.demonstrated | 121 |
| abstract_inverted_index.high-quality | 52 |
| abstract_inverted_index.limitations, | 72 |
| abstract_inverted_index.architecture, | 50 |
| abstract_inverted_index.oversmoothing | 75 |
| abstract_inverted_index.text-to-image | 53 |
| abstract_inverted_index.text-to-video | 55 |
| abstract_inverted_index.architectures, | 69 |
| abstract_inverted_index.understanding, | 106 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.07202925 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |