Optics and Precision Engineering, Volume. 32, Issue 20, 2987(2024)

Shape from polarization based on sparse self-attention

Zhichao YU1... Zhenhua WAN2 and Kaichun ZHAO1,* |Show fewer author(s)
Author Affiliations
  • 1Department of Precision Instrument, Tsinghua University, Beijing00084, China
  • 2Faculty of Mechanical Engineering, Guangxi University, Nanning530004; China
  • show less
    References(30)

    [1] Y L CAO, B J DING, J X CHEN et al. Photometric-stereo-based defect detection system for metal parts. Sensors, 22, 8374(2022).

    [2] Y F ZHANG, M X YE, S W XIANG et al. Scene-level surface normal estimation from encoded polarization representation, 3-14(2023).

    [3] C K YEH, N MATSUDA, X HUANG et al. A streamlined photometric stereo framework for cultural heritage, 738-752(2016).

    [4] M PENG, K C DI, Y X WANG et al. A photogrammetric-photometric stereo method for high-resolution lunar topographic mapping using Yutu-2 rover images. Remote Sensing, 13, 2975(2021).

    [5] M K JOHNSON, E H ADELSON. Shape estimation in natural illumination(2011).

    [6] B X SHI, Z P MO, Z WU et al. A benchmark dataset and evaluation for non-lambertian and uncalibrated photometric stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 271-284(2019).

    [7] Z YAO, K LI, Y FU et al. GPS-Net: Graph-based photometric stereo network(2020).

    [8] G Y CHEN, K HAN, B X SHI et al. Deep photometric stereo for non-lambertian surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 129-142(2022).

    [9] 王国珲, 卢彦汀. 深度学习技术在光度立体三维重建中的应用. 激光与光电子学进展, 60, 3788(2023).

         G H WANG, Y T LU. Application of deep learning technology to photometric stereo three-dimensional reconstruction. Laser & Optoelectronics Progress, 60, 3788(2023).

    [10] C Y LEI, C Y QI, J X XIE et al. Shape from polarization for complex scenes in the wild, 12622-12631(2022).

    [11] K KOSHIKAWA. A polarimetric approach to shape understanding of glossy objects. Advances in Robotics, 2, 190(1979).

    [12] J WANG, G M XU, J MA et al. Polarization computational imaging super-resolution reconstruction with lightweight attention cascading network. Opt. Precision Eng., 30, 2404-2419(2022).

         王杰, 徐国明, 马健. 轻量级注意力级联网络的偏振计算成像超分辨率重建. 光学 精密工程, 30, 2404-2419(2022).

    [14] Y YU, D Z ZHU, W A P SMITH. Shape-from-polarisation: a nonlinear least squares approach, 2969-2976(2017).

    [15] Y H BA, A GILBERT, F WANG et al. Deep shape from polarization, 554-571(2020).

    [16] S H ZOU, X X ZUO, Y M QIAN et al. 3D Human shape reconstruction from a polarization image, 351-368(2020).

    [17] C N WANG, K C ZHAO. Polarization image defogging based on dark channel prior principle. Opt. Precision Eng., 31, 3474-3481(2023).

         王楚宁, 赵开春. 基于暗通道先验原理的偏振图像去雾. 光学 精密工程, 31, 3474-3481(2023).

    [18] W JAKOB, S SPEIERER, N ROUSSEL et al. Mitsuba 3 renderer, http://github.com/mitsuba-renderer/mitsuba3(2022).

    [19] G C CHEN, L HE, Y S GUAN et al. Perspective phase angle model for polarimetric 3d reconstruction, 398-414(2022).

    [21] L ZHU, X J WANG, Z H KE et al. BiFormer: vision transformer with bi-level routing attention, 10323-10333(2023).

    [22] D P KINGMA, J BA. Adam: a method for stochastic optimization(2015).

    [23] W A P SMITH, R RAMAMOORTHI, S TOZZA. Height-from-polarisation with unknown lighting or albedo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 2875-2888(2019).

    [24] V DESCHAINTRE, Y M LIN, A GHOSH. Deep polarization imaging for 3D SHAPe and SVBRDF ACQUISition, 15562-15571(2021).

    [25] A H MAHMOUD, M T EL-MELEGY, A A FARAG. Direct method for shape recovery from POLARIZATIon and shading, 1769-1772(2012).

    [26] R ZHANG, X Y GUI, H Y CHENG et al. Target pose estimation based on polarization imaging in low light and strong background noise. Opt. Precision Eng., 29, 647-655(2021).

         张然, 桂心远, 成昊远. 基于偏振成像的低光照强背景噪声下的目标位姿估计. 光学 精密工程, 29, 647-655(2021).

    Tools

    Get Citation

    Copy Citation Text

    Zhichao YU, Zhenhua WAN, Kaichun ZHAO. Shape from polarization based on sparse self-attention[J]. Optics and Precision Engineering, 2024, 32(20): 2987

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: May. 9, 2024

    Accepted: --

    Published Online: Jan. 10, 2025

    The Author Email: ZHAO Kaichun (kaichunz@mail.tsinghua.edu.cn)

    DOI:10.37188/OPE.20243220.2987

    Topics