Publications
Detailed Information
Procrustean regression: A flexible alignment-based framework for nonrigid structure estimation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Sungheon | - |
dc.contributor.author | Lee, Minsik | - |
dc.contributor.author | Kwak, Nojun | - |
dc.creator | 곽노준 | - |
dc.date.accessioned | 2018-01-24T06:02:44Z | - |
dc.date.available | 2018-01-25T14:01:57Z | - |
dc.date.created | 2018-11-30 | - |
dc.date.issued | 2018-01 | - |
dc.identifier.citation | IEEE Transactions on Image Processing, Vol.27 No.1, pp.249-264 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | https://hdl.handle.net/10371/139286 | - |
dc.description.abstract | Non-rigid structure from motion (NRSfM) is a fundamental problem of computer vision. Recently, it has been shown that incorporating shape alignment in NRSfM can improve the performance significantly compared with the other algorithms, which do not consider shape alignment. However, realizing this idea was at a cost of a heavy, complicated process, which limits its usefulness and possible extensions. In this paper, we propose a novel regression framework for NRSfM, of which the variables (3D shapes) are regularized based on their aligned shapes. We show that this can be casted into an unconstrained problem or a problem with simple bound constraints, which can be efficiently solved by existing solvers. This framework can be easily integrated with numerous existing models and assumptions, such as orthographic or perspective camera models, occlusion, low-rank assumption, smooth deformations, and so on, which makes it more practical for various real situations. The experimental results show that the proposed method gives competitive result to the state-of-the-art methods for orthographic projection with much less time complexity and memory requirement, and outperforms the existing methods for perspective projection. | - |
dc.language | 영어 | - |
dc.language.iso | en | en |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.title | Procrustean regression: A flexible alignment-based framework for nonrigid structure estimation | - |
dc.type | Article | - |
dc.contributor.AlternativeAuthor | 박성헌 | - |
dc.contributor.AlternativeAuthor | 이민식 | - |
dc.contributor.AlternativeAuthor | 곽노준 | - |
dc.identifier.doi | 10.1109/TIP.2017.2757280 | - |
dc.citation.journaltitle | IEEE Transactions on Image Processing | - |
dc.identifier.wosid | 000414699100006 | - |
dc.identifier.scopusid | 2-s2.0-85030755619 | - |
dc.description.srnd | OAIID:RECH_ACHV_DSTSH_NO:T201715332 | - |
dc.description.srnd | RECH_ACHV_FG:RR00200001 | - |
dc.description.srnd | ADJUST_YN: | - |
dc.description.srnd | EMP_ID:A079380 | - |
dc.description.srnd | CITE_RATE:4.828 | - |
dc.description.srnd | DEPT_NM:융합과학부 | - |
dc.description.srnd | EMAIL:nojunk@snu.ac.kr | - |
dc.description.srnd | SCOPUS_YN:Y | - |
dc.description.srnd | CONFIRM:Y | - |
dc.citation.endpage | 264 | - |
dc.citation.number | 1 | - |
dc.citation.startpage | 249 | - |
dc.citation.volume | 27 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Kwak, Nojun | - |
dc.identifier.srnd | T201715332 | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordPlus | STRUCTURE-FROM-MOTION | - |
dc.subject.keywordPlus | 3D SHAPE | - |
dc.subject.keywordPlus | IMAGE STREAMS | - |
dc.subject.keywordPlus | RECOVERY | - |
dc.subject.keywordPlus | RECONSTRUCTION | - |
dc.subject.keywordPlus | FACTORIZATION | - |
dc.subject.keywordPlus | OPTIMIZATION | - |
dc.subject.keywordPlus | PRIORS | - |
dc.subject.keywordAuthor | Non-rigid structure from motion | - |
dc.subject.keywordAuthor | non-rigid shape analysis | - |
dc.subject.keywordAuthor | Procrustes analysis | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.