IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation Article Swipe
Juze Zhang
,
Shi Ye
,
Yuexin Ma
,
Lan Xu
,
Jingyi Yu
,
Jingya Wang
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.01058
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2302.01058
This paper presents an inverse kinematic optimization layer (IKOL) for 3D human pose and shape estimation that leverages the strength of both optimization- and regression-based methods within an end-to-end framework. IKOL involves a nonconvex optimization that establishes an implicit mapping from an image's 3D keypoints and body shapes to the relative body-part rotations. The 3D keypoints and the body shapes are the inputs and the relative body-part rotations are the solutions. However, this procedure is implicit and hard to make differentiable. So, to overcome this issue, we designed a Gauss-Newton differentiation (GN-Diff) procedure to differentiate IKOL. GN-Diff iteratively linearizes the nonconvex objective function to obtain Gauss-Newton directions with closed form solutions. Then, an automatic differentiation procedure is directly applied to generate a Jacobian matrix for end-to-end training. Notably, the GN-Diff procedure works fast because it does not rely on a time-consuming implicit differentiation procedure. The twist rotation and shape parameters are learned from the neural networks and, as a result, IKOL has a much lower computational overhead than most existing optimization-based methods. Additionally, compared to existing regression-based methods, IKOL provides a more accurate mesh-image correspondence. This is because it iteratively reduces the distance between the keypoints and also enhances the reliability of the pose structures. Extensive experiments demonstrate the superiority of our proposed framework over a wide range of 3D human pose and shape estimation methods.
Related Topics
Concepts
Pose
Jacobian matrix and determinant
Differentiable function
Computer science
Range (aeronautics)
Inverse kinematics
Inverse
3D pose estimation
Gauss
Mathematical optimization
Algorithm
Mathematics
Artificial intelligence
Applied mathematics
Geometry
Quantum mechanics
Materials science
Physics
Mathematical analysis
Composite material
Robot
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2302.01058
- https://arxiv.org/pdf/2302.01058
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4319166020
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4319166020Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2302.01058Digital Object Identifier
- Title
-
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-02-02Full publication date if available
- Authors
-
Juze Zhang, Shi Ye, Yuexin Ma, Lan Xu, Jingyi Yu, Jingya WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2302.01058Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2302.01058Direct 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/2302.01058Direct OA link when available
- Concepts
-
Pose, Jacobian matrix and determinant, Differentiable function, Computer science, Range (aeronautics), Inverse kinematics, Inverse, 3D pose estimation, Gauss, Mathematical optimization, Algorithm, Mathematics, Artificial intelligence, Applied mathematics, Geometry, Quantum mechanics, Materials science, Physics, Mathematical analysis, Composite material, RobotTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 1, 2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4319166020 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2302.01058 |
| ids.doi | https://doi.org/10.48550/arxiv.2302.01058 |
| ids.openalex | https://openalex.org/W4319166020 |
| fwci | 0.0 |
| type | preprint |
| title | IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10812 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9986000061035156 |
| 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 | Human Pose and Action Recognition |
| topics[1].id | https://openalex.org/T10531 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.996999979019165 |
| 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 | Advanced Vision and Imaging |
| topics[2].id | https://openalex.org/T12290 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9933000206947327 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2207 |
| topics[2].subfield.display_name | Control and Systems Engineering |
| topics[2].display_name | Human Motion and Animation |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C52102323 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7694768309593201 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1671968 |
| concepts[0].display_name | Pose |
| concepts[1].id | https://openalex.org/C200331156 |
| concepts[1].level | 2 |
| concepts[1].score | 0.718428909778595 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q506041 |
| concepts[1].display_name | Jacobian matrix and determinant |
| concepts[2].id | https://openalex.org/C202615002 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5757308006286621 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q783507 |
| concepts[2].display_name | Differentiable function |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5582030415534973 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C204323151 |
| concepts[4].level | 2 |
| concepts[4].score | 0.48513731360435486 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q905424 |
| concepts[4].display_name | Range (aeronautics) |
| concepts[5].id | https://openalex.org/C17816587 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4741610586643219 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1501872 |
| concepts[5].display_name | Inverse kinematics |
| concepts[6].id | https://openalex.org/C207467116 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4649715721607208 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q4385666 |
| concepts[6].display_name | Inverse |
| concepts[7].id | https://openalex.org/C36613465 |
| concepts[7].level | 3 |
| concepts[7].score | 0.46223336458206177 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q4636322 |
| concepts[7].display_name | 3D pose estimation |
| concepts[8].id | https://openalex.org/C161794534 |
| concepts[8].level | 2 |
| concepts[8].score | 0.46014297008514404 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q177493 |
| concepts[8].display_name | Gauss |
| concepts[9].id | https://openalex.org/C126255220 |
| concepts[9].level | 1 |
| concepts[9].score | 0.4239715039730072 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[9].display_name | Mathematical optimization |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.41411563754081726 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.38377436995506287 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C154945302 |
| concepts[12].level | 1 |
| concepts[12].score | 0.368832528591156 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[12].display_name | Artificial intelligence |
| concepts[13].id | https://openalex.org/C28826006 |
| concepts[13].level | 1 |
| concepts[13].score | 0.24327266216278076 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q33521 |
| concepts[13].display_name | Applied mathematics |
| concepts[14].id | https://openalex.org/C2524010 |
| concepts[14].level | 1 |
| concepts[14].score | 0.09516936540603638 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[14].display_name | Geometry |
| concepts[15].id | https://openalex.org/C62520636 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[15].display_name | Quantum mechanics |
| concepts[16].id | https://openalex.org/C192562407 |
| concepts[16].level | 0 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[16].display_name | Materials science |
| concepts[17].id | https://openalex.org/C121332964 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[17].display_name | Physics |
| concepts[18].id | https://openalex.org/C134306372 |
| concepts[18].level | 1 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[18].display_name | Mathematical analysis |
| concepts[19].id | https://openalex.org/C159985019 |
| concepts[19].level | 1 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[19].display_name | Composite material |
| concepts[20].id | https://openalex.org/C90509273 |
| concepts[20].level | 2 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q11012 |
| concepts[20].display_name | Robot |
| keywords[0].id | https://openalex.org/keywords/pose |
| keywords[0].score | 0.7694768309593201 |
| keywords[0].display_name | Pose |
| keywords[1].id | https://openalex.org/keywords/jacobian-matrix-and-determinant |
| keywords[1].score | 0.718428909778595 |
| keywords[1].display_name | Jacobian matrix and determinant |
| keywords[2].id | https://openalex.org/keywords/differentiable-function |
| keywords[2].score | 0.5757308006286621 |
| keywords[2].display_name | Differentiable function |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5582030415534973 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/range |
| keywords[4].score | 0.48513731360435486 |
| keywords[4].display_name | Range (aeronautics) |
| keywords[5].id | https://openalex.org/keywords/inverse-kinematics |
| keywords[5].score | 0.4741610586643219 |
| keywords[5].display_name | Inverse kinematics |
| keywords[6].id | https://openalex.org/keywords/inverse |
| keywords[6].score | 0.4649715721607208 |
| keywords[6].display_name | Inverse |
| keywords[7].id | https://openalex.org/keywords/3d-pose-estimation |
| keywords[7].score | 0.46223336458206177 |
| keywords[7].display_name | 3D pose estimation |
| keywords[8].id | https://openalex.org/keywords/gauss |
| keywords[8].score | 0.46014297008514404 |
| keywords[8].display_name | Gauss |
| keywords[9].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[9].score | 0.4239715039730072 |
| keywords[9].display_name | Mathematical optimization |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.41411563754081726 |
| keywords[10].display_name | Algorithm |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.38377436995506287 |
| keywords[11].display_name | Mathematics |
| keywords[12].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[12].score | 0.368832528591156 |
| keywords[12].display_name | Artificial intelligence |
| keywords[13].id | https://openalex.org/keywords/applied-mathematics |
| keywords[13].score | 0.24327266216278076 |
| keywords[13].display_name | Applied mathematics |
| keywords[14].id | https://openalex.org/keywords/geometry |
| keywords[14].score | 0.09516936540603638 |
| keywords[14].display_name | Geometry |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2302.01058 |
| 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/2302.01058 |
| 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/2302.01058 |
| locations[1].id | doi:10.48550/arxiv.2302.01058 |
| 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.2302.01058 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5018141009 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Juze Zhang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhang, Juze |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5017327360 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9625-8222 |
| authorships[1].author.display_name | Shi Ye |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Shi, Ye |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102015139 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7237-988X |
| authorships[2].author.display_name | Yuexin Ma |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ma, Yuexin |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100756916 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-8333-7589 |
| authorships[3].author.display_name | Lan Xu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Xu, Lan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100564692 |
| authorships[4].author.orcid | https://orcid.org/0009-0001-7113-3893 |
| authorships[4].author.display_name | Jingyi Yu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yu, Jingyi |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100639520 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-5618-7498 |
| authorships[5].author.display_name | Jingya Wang |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Wang, Jingya |
| authorships[5].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/2302.01058 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-02-04T00:00:00 |
| display_name | IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10812 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9986000061035156 |
| 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 | Human Pose and Action Recognition |
| related_works | https://openalex.org/W2115240519, https://openalex.org/W4253893311, https://openalex.org/W2113785214, https://openalex.org/W2080642692, https://openalex.org/W2798721181, https://openalex.org/W3201205132, https://openalex.org/W2039927751, https://openalex.org/W4287600488, https://openalex.org/W4312694060, https://openalex.org/W4386075737 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2302.01058 |
| 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/2302.01058 |
| 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/2302.01058 |
| primary_location.id | pmh:oai:arXiv.org:2302.01058 |
| 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/2302.01058 |
| 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/2302.01058 |
| publication_date | 2023-02-02 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 32, 88, 121, 139, 158, 162, 180, 215 |
| abstract_inverted_index.3D | 10, 43, 54, 219 |
| abstract_inverted_index.an | 3, 27, 37, 41, 112 |
| abstract_inverted_index.as | 157 |
| abstract_inverted_index.is | 74, 116, 186 |
| abstract_inverted_index.it | 134, 188 |
| abstract_inverted_index.of | 20, 201, 210, 218 |
| abstract_inverted_index.on | 138 |
| abstract_inverted_index.to | 48, 78, 82, 93, 103, 119, 174 |
| abstract_inverted_index.we | 86 |
| abstract_inverted_index.So, | 81 |
| abstract_inverted_index.The | 53, 144 |
| abstract_inverted_index.and | 13, 23, 45, 56, 63, 76, 147, 196, 222 |
| abstract_inverted_index.are | 60, 68, 150 |
| abstract_inverted_index.for | 9, 124 |
| abstract_inverted_index.has | 161 |
| abstract_inverted_index.not | 136 |
| abstract_inverted_index.our | 211 |
| abstract_inverted_index.the | 18, 49, 57, 61, 64, 69, 99, 128, 153, 191, 194, 199, 202, 208 |
| abstract_inverted_index.IKOL | 30, 160, 178 |
| abstract_inverted_index.This | 0, 185 |
| abstract_inverted_index.also | 197 |
| abstract_inverted_index.and, | 156 |
| abstract_inverted_index.body | 46, 58 |
| abstract_inverted_index.both | 21 |
| abstract_inverted_index.does | 135 |
| abstract_inverted_index.fast | 132 |
| abstract_inverted_index.form | 109 |
| abstract_inverted_index.from | 40, 152 |
| abstract_inverted_index.hard | 77 |
| abstract_inverted_index.make | 79 |
| abstract_inverted_index.more | 181 |
| abstract_inverted_index.most | 168 |
| abstract_inverted_index.much | 163 |
| abstract_inverted_index.over | 214 |
| abstract_inverted_index.pose | 12, 203, 221 |
| abstract_inverted_index.rely | 137 |
| abstract_inverted_index.than | 167 |
| abstract_inverted_index.that | 16, 35 |
| abstract_inverted_index.this | 72, 84 |
| abstract_inverted_index.wide | 216 |
| abstract_inverted_index.with | 107 |
| abstract_inverted_index.IKOL. | 95 |
| abstract_inverted_index.Then, | 111 |
| abstract_inverted_index.human | 11, 220 |
| abstract_inverted_index.layer | 7 |
| abstract_inverted_index.lower | 164 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.range | 217 |
| abstract_inverted_index.shape | 14, 148, 223 |
| abstract_inverted_index.twist | 145 |
| abstract_inverted_index.works | 131 |
| abstract_inverted_index.(IKOL) | 8 |
| abstract_inverted_index.closed | 108 |
| abstract_inverted_index.inputs | 62 |
| abstract_inverted_index.issue, | 85 |
| abstract_inverted_index.matrix | 123 |
| abstract_inverted_index.neural | 154 |
| abstract_inverted_index.obtain | 104 |
| abstract_inverted_index.shapes | 47, 59 |
| abstract_inverted_index.within | 26 |
| abstract_inverted_index.GN-Diff | 96, 129 |
| abstract_inverted_index.applied | 118 |
| abstract_inverted_index.because | 133, 187 |
| abstract_inverted_index.between | 193 |
| abstract_inverted_index.image's | 42 |
| abstract_inverted_index.inverse | 4 |
| abstract_inverted_index.learned | 151 |
| abstract_inverted_index.mapping | 39 |
| abstract_inverted_index.methods | 25 |
| abstract_inverted_index.reduces | 190 |
| abstract_inverted_index.result, | 159 |
| abstract_inverted_index.However, | 71 |
| abstract_inverted_index.Jacobian | 122 |
| abstract_inverted_index.Notably, | 127 |
| abstract_inverted_index.accurate | 182 |
| abstract_inverted_index.compared | 173 |
| abstract_inverted_index.designed | 87 |
| abstract_inverted_index.directly | 117 |
| abstract_inverted_index.distance | 192 |
| abstract_inverted_index.enhances | 198 |
| abstract_inverted_index.existing | 169, 175 |
| abstract_inverted_index.function | 102 |
| abstract_inverted_index.generate | 120 |
| abstract_inverted_index.implicit | 38, 75, 141 |
| abstract_inverted_index.involves | 31 |
| abstract_inverted_index.methods, | 177 |
| abstract_inverted_index.methods. | 171, 225 |
| abstract_inverted_index.networks | 155 |
| abstract_inverted_index.overcome | 83 |
| abstract_inverted_index.overhead | 166 |
| abstract_inverted_index.presents | 2 |
| abstract_inverted_index.proposed | 212 |
| abstract_inverted_index.provides | 179 |
| abstract_inverted_index.relative | 50, 65 |
| abstract_inverted_index.rotation | 146 |
| abstract_inverted_index.strength | 19 |
| abstract_inverted_index.(GN-Diff) | 91 |
| abstract_inverted_index.Extensive | 205 |
| abstract_inverted_index.automatic | 113 |
| abstract_inverted_index.body-part | 51, 66 |
| abstract_inverted_index.framework | 213 |
| abstract_inverted_index.keypoints | 44, 55, 195 |
| abstract_inverted_index.kinematic | 5 |
| abstract_inverted_index.leverages | 17 |
| abstract_inverted_index.nonconvex | 33, 100 |
| abstract_inverted_index.objective | 101 |
| abstract_inverted_index.procedure | 73, 92, 115, 130 |
| abstract_inverted_index.rotations | 67 |
| abstract_inverted_index.training. | 126 |
| abstract_inverted_index.directions | 106 |
| abstract_inverted_index.end-to-end | 28, 125 |
| abstract_inverted_index.estimation | 15, 224 |
| abstract_inverted_index.framework. | 29 |
| abstract_inverted_index.linearizes | 98 |
| abstract_inverted_index.mesh-image | 183 |
| abstract_inverted_index.parameters | 149 |
| abstract_inverted_index.procedure. | 143 |
| abstract_inverted_index.rotations. | 52 |
| abstract_inverted_index.solutions. | 70, 110 |
| abstract_inverted_index.demonstrate | 207 |
| abstract_inverted_index.establishes | 36 |
| abstract_inverted_index.experiments | 206 |
| abstract_inverted_index.iteratively | 97, 189 |
| abstract_inverted_index.reliability | 200 |
| abstract_inverted_index.structures. | 204 |
| abstract_inverted_index.superiority | 209 |
| abstract_inverted_index.Gauss-Newton | 89, 105 |
| abstract_inverted_index.optimization | 6, 34 |
| abstract_inverted_index.Additionally, | 172 |
| abstract_inverted_index.computational | 165 |
| abstract_inverted_index.differentiate | 94 |
| abstract_inverted_index.optimization- | 22 |
| abstract_inverted_index.time-consuming | 140 |
| abstract_inverted_index.correspondence. | 184 |
| abstract_inverted_index.differentiable. | 80 |
| abstract_inverted_index.differentiation | 90, 114, 142 |
| abstract_inverted_index.regression-based | 24, 176 |
| abstract_inverted_index.optimization-based | 170 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |