6533b7defe1ef96bd12765d6

RESEARCH PRODUCT

Quality Assessment of Reconstruction and Relighting from RTI Images: Application to Manufactured Surfaces

Yuly CastroGaëtan Le GoïcAlamin MansouriMarius PedersenJean-baptiste ThomasMarvin NuritAbir Zendagui

subject

0209 industrial biotechnologyComputer sciencebusiness.industryQuality assessmentmedia_common.quotation_subject02 engineering and technologyIterative reconstruction020901 industrial engineering & automationVisual assessment0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionQuality (business)Relevance (information retrieval)Artificial intelligenceSampling densityPolynomial texture mappingbusinessSurface reconstructionmedia_common

description

In this paper, we propose to evaluate the quality of the reconstruction and relighting from images acquired by a Reflectance Transformation Imaging (RTI) device. Three relighting models, namely the PTM, HSH and DMD, are evaluated using PSNR and SSIM. A visual assessment of how the reconstructed surfaces are perceived is also carried out through a sensory experiment. This study allows to estimate the relevance of these models to reproduce the appearance of the manufactured surfaces. It also shows that DMD reproduces the most accurate reconstruction/relighting to an acquired measurement and that a higher sampling density don't mean necessarily a higher perceptual quality.

yearjournalcountryeditionlanguage
2019-11-012019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)
https://doi.org/10.1109/sitis.2019.00121