DiLiGenRT: A Photometric Stereo Dataset with Quantified Roughness and Translucency
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11810-11820
Abstract
Photometric stereo faces challenges from non-Lambertian reflectance in real-world scenarios. Systematically measuring the reliability of photometric stereo methods in handling such complex reflectance necessitates a real-world dataset with quantitatively controlled reflectances. This paper introduces DiLiGenRT, the first real-world dataset for evaluating photometric stereo methods under quantified reflectances by manufacturing 54 hemispheres with varying degrees of two reflectance properties: Roughness and Transluency, Unlike qualitative and semantic labels, such as “diffuse” and “specular,” that have been used in previous datasets, our quantified dataset allows comprehensive and systematic benchmark evaluations. In addition, it facilitates selecting best-fit photometric stereo methods based on the quantitative reflectance properties. Our dataset and benchmark results are available at https://photometricstereo.github.io/diligentrt.html.Keywords
This publication has 48 references indexed in Scilit:
- DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images2022
- Self-calibrating Photometric Stereo by Neural Inverse Rendering2022
- NormAttention-PSN: A High-frequency Region Enhanced Photometric Stereo Network with Normalized AttentionInternational Journal of Computer Vision, 2022
- The Bouguer‐Beer‐Lambert Law: Shining Light on the ObscureChemphyschem, 2020
- CNN-PS: CNN-Based Photometric Stereo for General Non-convex Surfaces2018
- PS-FCN: A Flexible Learning Framework for Photometric Stereo2018
- Surface Normal Deconvolution: Photometric Stereo for Optically Thick Translucent Objects2014
- A Closed-Form, Consistent and Robust Solution to Uncalibrated Photometric Stereo Via Local Diffuse Reflectance MaximaInternational Journal of Computer Vision, 2013
- Robust Photometric Stereo via Low-Rank Matrix Completion and Recovery2011
- Ring-Light Photometric Stereo2010