DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform Article Swipe
Hung T. Nguyen
,
B. Li
,
Truong Thanh Nguyen
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.12637
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.12637
Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence and reliance on dense training views. To this end, we present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding. It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views. Our DWTNeRF additionally includes a novel Discrete Wavelet loss that allows explicit prioritization of low frequencies directly in the training objective, reducing few-shot NeRF's overfitting on high frequencies in earlier training stages. We also introduce a model-based approach, based on multi-head attention, that is compatible with INGP, which are sensitive to architectural changes. On the 3-shot LLFF benchmark, DWTNeRF outperforms Vanilla INGP by 15.07% in PSNR, 24.45% in SSIM and 36.30% in LPIPS. Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.12637
- https://arxiv.org/pdf/2501.12637
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406779007
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406779007Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.12637Digital Object Identifier
- Title
-
DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet TransformWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-22Full publication date if available
- Authors
-
Hung T. Nguyen, B. Li, Truong Thanh NguyenList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.12637Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.12637Direct 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/2501.12637Direct OA link when available
- Concepts
-
Boosting (machine learning), Radiance, Discrete wavelet transform, Artificial intelligence, Shot (pellet), Computer science, Wavelet, Computer vision, Pattern recognition (psychology), Wavelet transform, Geology, Remote sensing, Materials science, MetallurgyTop 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/W4406779007 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.12637 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.12637 |
| ids.openalex | https://openalex.org/W4406779007 |
| fwci | |
| type | preprint |
| title | DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9704999923706055 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T13114 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9327999949455261 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2214 |
| topics[1].subfield.display_name | Media Technology |
| topics[1].display_name | Image Processing Techniques and Applications |
| topics[2].id | https://openalex.org/T10688 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9186000227928162 |
| 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 | Image and Signal Denoising Methods |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C46686674 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8130955696105957 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q466303 |
| concepts[0].display_name | Boosting (machine learning) |
| concepts[1].id | https://openalex.org/C23690007 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6461576223373413 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1411145 |
| concepts[1].display_name | Radiance |
| concepts[2].id | https://openalex.org/C46286280 |
| concepts[2].level | 4 |
| concepts[2].score | 0.6183643937110901 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2414958 |
| concepts[2].display_name | Discrete wavelet transform |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5510056614875793 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C2778344882 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5321300029754639 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q278938 |
| concepts[4].display_name | Shot (pellet) |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.5036768317222595 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C47432892 |
| concepts[6].level | 2 |
| concepts[6].score | 0.46614542603492737 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q831390 |
| concepts[6].display_name | Wavelet |
| concepts[7].id | https://openalex.org/C31972630 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3717741370201111 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[7].display_name | Computer vision |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.34197813272476196 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C196216189 |
| concepts[9].level | 3 |
| concepts[9].score | 0.323738694190979 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2867 |
| concepts[9].display_name | Wavelet transform |
| concepts[10].id | https://openalex.org/C127313418 |
| concepts[10].level | 0 |
| concepts[10].score | 0.22438210248947144 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[10].display_name | Geology |
| concepts[11].id | https://openalex.org/C62649853 |
| concepts[11].level | 1 |
| concepts[11].score | 0.20258304476737976 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q199687 |
| concepts[11].display_name | Remote sensing |
| concepts[12].id | https://openalex.org/C192562407 |
| concepts[12].level | 0 |
| concepts[12].score | 0.08524462580680847 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[12].display_name | Materials science |
| concepts[13].id | https://openalex.org/C191897082 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q11467 |
| concepts[13].display_name | Metallurgy |
| keywords[0].id | https://openalex.org/keywords/boosting |
| keywords[0].score | 0.8130955696105957 |
| keywords[0].display_name | Boosting (machine learning) |
| keywords[1].id | https://openalex.org/keywords/radiance |
| keywords[1].score | 0.6461576223373413 |
| keywords[1].display_name | Radiance |
| keywords[2].id | https://openalex.org/keywords/discrete-wavelet-transform |
| keywords[2].score | 0.6183643937110901 |
| keywords[2].display_name | Discrete wavelet transform |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5510056614875793 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/shot |
| keywords[4].score | 0.5321300029754639 |
| keywords[4].display_name | Shot (pellet) |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.5036768317222595 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/wavelet |
| keywords[6].score | 0.46614542603492737 |
| keywords[6].display_name | Wavelet |
| keywords[7].id | https://openalex.org/keywords/computer-vision |
| keywords[7].score | 0.3717741370201111 |
| keywords[7].display_name | Computer vision |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.34197813272476196 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/wavelet-transform |
| keywords[9].score | 0.323738694190979 |
| keywords[9].display_name | Wavelet transform |
| keywords[10].id | https://openalex.org/keywords/geology |
| keywords[10].score | 0.22438210248947144 |
| keywords[10].display_name | Geology |
| keywords[11].id | https://openalex.org/keywords/remote-sensing |
| keywords[11].score | 0.20258304476737976 |
| keywords[11].display_name | Remote sensing |
| keywords[12].id | https://openalex.org/keywords/materials-science |
| keywords[12].score | 0.08524462580680847 |
| keywords[12].display_name | Materials science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.12637 |
| 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/2501.12637 |
| 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/2501.12637 |
| locations[1].id | doi:10.48550/arxiv.2501.12637 |
| 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.2501.12637 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100716476 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3373-8178 |
| authorships[0].author.display_name | Hung T. Nguyen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nguyen, Hung |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5071418849 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | B. Li |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Blark Runfa |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101495770 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3139-4105 |
| authorships[2].author.display_name | Truong Thanh Nguyen |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Nguyen, Truong |
| authorships[2].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/2501.12637 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9704999923706055 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Neural Networks and Applications |
| related_works | https://openalex.org/W2085792030, https://openalex.org/W1588899229, https://openalex.org/W2172291505, https://openalex.org/W2023142747, https://openalex.org/W2037009764, https://openalex.org/W2063036707, https://openalex.org/W2501033992, https://openalex.org/W2377605153, https://openalex.org/W1967182499, https://openalex.org/W2088723847 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.12637 |
| 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/2501.12637 |
| 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/2501.12637 |
| primary_location.id | pmh:oai:arXiv.org:2501.12637 |
| 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/2501.12637 |
| 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/2501.12637 |
| publication_date | 2025-01-22 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 37, 66, 97, 138 |
| abstract_inverted_index.3D | 13 |
| abstract_inverted_index.It | 46 |
| abstract_inverted_index.On | 115 |
| abstract_inverted_index.To | 31 |
| abstract_inverted_index.We | 94 |
| abstract_inverted_index.by | 22, 124 |
| abstract_inverted_index.in | 8, 79, 90, 126, 129, 133 |
| abstract_inverted_index.is | 47, 105 |
| abstract_inverted_index.of | 75, 140 |
| abstract_inverted_index.on | 27, 41, 58, 87, 101 |
| abstract_inverted_index.or | 150 |
| abstract_inverted_index.to | 112 |
| abstract_inverted_index.we | 34 |
| abstract_inverted_index.Our | 62, 135 |
| abstract_inverted_index.and | 12, 25, 131 |
| abstract_inverted_index.are | 20, 110 |
| abstract_inverted_index.but | 16 |
| abstract_inverted_index.for | 53, 144 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.its | 17 |
| abstract_inverted_index.low | 76 |
| abstract_inverted_index.the | 80, 116 |
| abstract_inverted_index.INGP | 123, 149 |
| abstract_inverted_index.LLFF | 118 |
| abstract_inverted_index.SSIM | 130 |
| abstract_inverted_index.also | 95 |
| abstract_inverted_index.end, | 33 |
| abstract_inverted_index.hash | 44 |
| abstract_inverted_index.high | 88 |
| abstract_inverted_index.like | 148 |
| abstract_inverted_index.loss | 70 |
| abstract_inverted_index.slow | 23 |
| abstract_inverted_index.that | 71, 104 |
| abstract_inverted_index.this | 32 |
| abstract_inverted_index.view | 10 |
| abstract_inverted_index.with | 49, 107 |
| abstract_inverted_index.3DGS. | 151 |
| abstract_inverted_index.INGP, | 108 |
| abstract_inverted_index.NeRF, | 55 |
| abstract_inverted_index.PSNR, | 127 |
| abstract_inverted_index.based | 40, 100 |
| abstract_inverted_index.dense | 28 |
| abstract_inverted_index.novel | 9, 67 |
| abstract_inverted_index.scene | 14 |
| abstract_inverted_index.terms | 51 |
| abstract_inverted_index.which | 56, 109 |
| abstract_inverted_index.(NeRF) | 3 |
| abstract_inverted_index.15.07% | 125 |
| abstract_inverted_index.24.45% | 128 |
| abstract_inverted_index.3-shot | 117 |
| abstract_inverted_index.36.30% | 132 |
| abstract_inverted_index.Fields | 2 |
| abstract_inverted_index.LPIPS. | 134 |
| abstract_inverted_index.NeRF's | 85 |
| abstract_inverted_index.Neural | 0 |
| abstract_inverted_index.allows | 72 |
| abstract_inverted_index.sparse | 59 |
| abstract_inverted_index.views. | 30, 61 |
| abstract_inverted_index.DWTNeRF | 63, 120 |
| abstract_inverted_index.Vanilla | 122 |
| abstract_inverted_index.Wavelet | 69 |
| abstract_inverted_index.coupled | 48 |
| abstract_inverted_index.current | 141 |
| abstract_inverted_index.earlier | 91 |
| abstract_inverted_index.present | 35 |
| abstract_inverted_index.stages. | 93 |
| abstract_inverted_index.unified | 38 |
| abstract_inverted_index.DWTNeRF, | 36 |
| abstract_inverted_index.Discrete | 68 |
| abstract_inverted_index.Radiance | 1 |
| abstract_inverted_index.achieved | 5 |
| abstract_inverted_index.approach | 136 |
| abstract_inverted_index.changes. | 114 |
| abstract_inverted_index.designed | 52 |
| abstract_inverted_index.directly | 78 |
| abstract_inverted_index.explicit | 73 |
| abstract_inverted_index.few-shot | 54, 84, 142 |
| abstract_inverted_index.hindered | 21 |
| abstract_inverted_index.implicit | 146 |
| abstract_inverted_index.includes | 65 |
| abstract_inverted_index.operates | 57 |
| abstract_inverted_index.reducing | 83 |
| abstract_inverted_index.reliance | 26 |
| abstract_inverted_index.superior | 6 |
| abstract_inverted_index.training | 29, 60, 81, 92 |
| abstract_inverted_index.approach, | 99 |
| abstract_inverted_index.encoding. | 45 |
| abstract_inverted_index.framework | 39 |
| abstract_inverted_index.introduce | 96 |
| abstract_inverted_index.practical | 18 |
| abstract_inverted_index.sensitive | 111 |
| abstract_inverted_index.synthesis | 11 |
| abstract_inverted_index.approaches | 143 |
| abstract_inverted_index.attention, | 103 |
| abstract_inverted_index.benchmark, | 119 |
| abstract_inverted_index.compatible | 106 |
| abstract_inverted_index.encourages | 137 |
| abstract_inverted_index.multi-head | 102 |
| abstract_inverted_index.objective, | 82 |
| abstract_inverted_index.convergence | 24 |
| abstract_inverted_index.frequencies | 77, 89 |
| abstract_inverted_index.model-based | 98 |
| abstract_inverted_index.outperforms | 121 |
| abstract_inverted_index.overfitting | 86 |
| abstract_inverted_index.performance | 7 |
| abstract_inverted_index.re-thinking | 139 |
| abstract_inverted_index.additionally | 64 |
| abstract_inverted_index.applications | 19 |
| abstract_inverted_index.Instant-NGP's | 42 |
| abstract_inverted_index.architectural | 113 |
| abstract_inverted_index.fast-training | 43 |
| abstract_inverted_index.prioritization | 74 |
| abstract_inverted_index.regularization | 50 |
| abstract_inverted_index.fast-converging | 145 |
| abstract_inverted_index.representation, | 15 |
| abstract_inverted_index.representations | 147 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |