A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataset

Show simple item record
dc.contributor.authorHardy, Clément
dc.contributor.authorQuéau, Yvain
dc.contributor.authorTschumperlé, David
dc.contributor.editorSkala, Václav
dc.date.accessioned2023-10-17T15:22:54Z
dc.date.available2023-10-17T15:22:54Z
dc.date.issued2023
dc.description.abstract-translatedThe photometric stereo (PS) problem consists in reconstructing the 3D-surface of an object, thanks to a set of photographs taken under different lighting directions. In this paper, we propose a multi-scale architecture for PS which, combined with a new dataset, yields state-of-the-art results. Our proposed architecture is flexible: it permits to consider a variable number of images as well as variable image size without loss of performance. In addition, we define a set of constraints to allow the generation of a relevant synthetic dataset to train convolutional neural networks for the PS problem. Our proposed dataset is much larger than pre-existing ones, and contains many objects with challenging materials having anisotropic reflectance (e.g. metals, glass). We show on publicly available benchmarks that the combination of both these contributions drastically improves the accuracy of the estimated normal field, in comparison with previous state-of-the-art methods.en
dc.format10 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationWSCG 2023: full papers proceedings: 1. International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, p. 194-203.en
dc.identifier.doihttps://www.doi.org/10.24132/CSRN.3301.23
dc.identifier.isbn978-80-86943-32-9
dc.identifier.issn2464–4617 (print)
dc.identifier.issn2464–4625 (CD/DVD)
dc.identifier.urihttp://hdl.handle.net/11025/54425
dc.language.isoenen
dc.publisherVáclav Skala - UNION Agencyen
dc.rights© Václav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectfotometrické stereocs
dc.subject3D rekonstrukcecs
dc.subjectběžný mapový odhadcs
dc.subjectvíceúrovňová architekturacs
dc.subjectnový datový souborcs
dc.subject.translatedphotometric stereoen
dc.subject.translated3D-recontructionen
dc.subject.translatednormal map estimationen
dc.subject.translatedmulti-scale achitectureen
dc.subject.translatednew dataseten
dc.titleA Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataseten
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
F43-full.pdf
Size:
3.78 MB
Format:
Adobe Portable Document Format
Description:
Plný text
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

WSCG 2023: Full Papers Proceedings