SRPS–deep-learning-based photometric stereo using superresolution images

다국어 초록 (Multilingual Abstract)

This paper introduces a novel deep-learning-based photometric stereo method that uses superresolution (SR) images: SR photometric stereo. Recent deep-learning-based SR algorithms have yielded great results in terms of enlarging images without mosaic effects. Supposing that the SR algorithms successfully enhance the feature and colour information of original images, implementing SR images using the photometric stereo method facilitates the use of considerably more information on the object than existing photometric stereo methods. We built a novel deep-learning-based network for the photometric stereo technique to optimize the input–output of SR image inputs and normal map outputs. We tested our network using the most widely used benchmark dataset and obtained better results than existing photometric stereo methods.

참고문헌 (Reference)

1 Zheng, H., "Wavelet-based nonlocal-means super resolution for video sequences" 2817-2820, 2010

2 Ronneberger, O., "U-net: Convolutional networks for biomedical image segmentation" 234-241, 2015

3 Makwana, R. R., "Survey on single image super resolution techniques" 5 : 23-33, 2013

4 Liyakathunisa, "Superresolution blind reconstruction of low-resolution images using wavelets based fusion" 40 : 177-181, 2008

5 Zheng, Q., "Summary study of data-driven photometric stereo methods" 2 : 213-221, 2020

6 Zheng, Q., "SPLINE-Net: Sparse photometric stereo through lighting interpolation and normal estimation networks" 8549-8558, 2019

7 Wu, L., "Robust photometric stereo via low-rank matrix completion and recovery" 703-717, 2010

8 Einarsson, P., "Relighting human locomotion with flowed reflectance fields" 183-194, 2006

9 Iwahori, Y., "Principal components analysis and neural network implementation of photometric stereo" 117-, 1995

10 Alldrin, N., "Photometric stereo with non-parametric and spatially-varying reflectance" 1-8, 2008

11 Ikehata, S., "Photometric stereo using constrained bivariate regression for general isotropic surfaces" 2179-2186, 2014

12 Hayakawa, H., "Photometric stereo under a light source with arbitrary motion" 11 : 3079-3089, 1994

13 Woodham, R. J., "Photometric method for determining surface orientation frommultiple images" 19 : 191139-, 1980

14 Chen, G., "PS-FCN: A flexible learning framework for photometric stereo" 3-18, 2018

15 Jin, J., "Light field spatial super-resolution via deep combinatorial geometry embedding and structural consistency regularization" 2260-2269, 2020

16 Li, J., "Learning to minify photometric stereo" 7568-7576, 2019

17 Dong, C., "Learning a deep convolutional network for image super-resolution" 184-199, 2014

18 Mei, Y., "Image super-resolution with cross-scale non-local attention and exhaustive self-exemplars mining" 5690-5699, 2020

19 Zhang, Y., "Image super-resolution using very deep residual channel attention networks" 286-301, 2018

20 Patel, V., "Hybrid approach for single image super resolution using ISEF and IBP" 495-499, 2011

21 Jiang, K., "Hierarchical dense recursive network for image super-resolution" 107 : 107475-, 2020

22 Lim, B., "Enhanced deep residual networks for single image super-resolution" 136-144, 2017

23 He, K., "Deep residual learning for image recognition" 770-778, 2016

24 Santo, H., "Deep photometric stereo network" 501-509, 2017

25 Keras, "Deep learning for humans"

26 Guanying Chen, "Deep Photometric Stereo for Non-Lambertian Surfaces" Institute of Electrical and Electronics Engineers (IEEE) 1-1, 2020

27 Zhihao Wang, "Deep Learning for Image Super-Resolution: A Survey" Institute of Electrical and Electronics Engineers (IEEE) 43 (43): 3365-3387, 2021

28 Ikehata, S., "CNN-PS: CNN-based photometric stereo for general non-convex surfaces" 3-18, 2018

29 Shi, B., "Bipolynomial modeling of low-frequency reflectances" 36 : 1078-1091, 2013

30 Kingma, D. P., "Adam: A method for stochastic optimization"

31 Kim, J., "Accurate image superresolution using very deep convolutional networks" 1646-1654, 2016

32 Chen, L., "A microfacet-basedmodel for photometric stereo with general isotropic reflectance" 43 : 48-61, 2019

33 Shi, B., "A benchmark dataset and evaluation for non-Lambertian and uncalibrated photometric stereo" 3707-3716, 2016