Abstract
For the shortcomings of current 3D reconstruction models such as poor reconstruction effect and blurred edges when dealing with weakly textured and textureless objects, this paper fuses the rich polarization spectral information with multi-view 3D reconstruction and presents the MP-mip-NeRf 360 model. This paper has constructed a multi-angle polarization dataset and systematic theoretical model validations are completed on this dataset. Compared with existing deep learning models, our model achieves better results in terms of accuracy, rendering more realistic scenes and obtaining more detailed depth maps.
This work is supported by the National Natural Science Foundation of China (No. 62261016, No. 62077002), the Key Research and Development Program of Guilin (No. 20210214-2) and the Key Research and Development Program of Guangxi (No. AB18050014).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Song, W., et al.: Three-dimensional reconstruction for photon counting imaging using a planar catadioptric method. In: Conference on Lasers and Electro-Optics/Pacific Rim. Optica Publishing Group (2017)
Wang, B., et al.: Design of three-dimensional reconstruction and robot path planning based on kinect system. In: 2017 29th Chinese Control And Decision Conference (CCDC). IEEE (2017)
Zhang, J., et al.: Three-dimensional reconstruction method based on target recognition for binocular humanoid robot. In: 2016 International Conference on Progress in Informatics and Computing (PIC). IEEE (2016)
Cui, Z., et al.: Polarimetric multi-view stereo. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Zhu, D., Smith, W.A.P.: Depth from a polarisation+ RGB stereo pair. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Zhang, R.H., et al.: Polarised multi-view 3D reconstruction based on parallax angle and zenith angle optimisation. J. Infrared Millim. Waves 40(1), 133–142 (2021)
Zhao, J., Monno, Y., Okutomi, M.: Polarimetric multi-view inverse rendering. IEEE Trans. Pattern Anal. Mach. Intell. (2022)
Wu, X., et al.: Three dimensional shape reconstruction via polarization imaging and deep learning. Sensors 23(10), 4592 (2023)
Mildenhall, B., et al.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99–106 (2021)
Barron, J.T., et al.: Mip-nerf: a multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)
Barron, J.T., et al.: Mip-nerf 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
Zhang, K., et al.: Nerf++: analyzing and improving neural radiance fields (2020). arxiv:2010.07492
Hore, A., Ziou, D.: Image quality metrics: PSNR vs. SSIM. In: 2010 20th International Conference on Pattern Recognition. IEEE (2010)
Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Shurcliff, W.A.: Polarized Light: Production and Use. Harvard University Press (1962)
Wolff, L.B.: Polarization vision: a new sensory approach to image understanding. Image Vis. Comput. 15(2), 81–93 (1997)
Atkinson, G.A.: Two-source surface reconstruction using polarisation. In: Image Analysis: 20th Scandinavian Conference, SCIA 2017, Tromsø, Norway, 12–14 June 2017, Proceedings, Part II 20. Springer International Publishing (2017)
Lavigne, D.A., et al.: Target discrimination of man-made objects using passive polarimetric signatures acquired in the visible and infrared spectral bands. In: Polarization Science and Remote Sensing V, vol. 8160. SPIE (2011)
Fei, C.: Research on image fusion based on intelligent optimisation and visual saliency. Doctoral dissertation. University of Electronic Science and Technology (2015)
Han, D., Li, L., Guo, X., Ma, J.: Multi-exposure image fusion via deep perceptual enhancement. Inf. Fusion 79, 248–262 (2021)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, 5–9 Oct 2015, proceedings, part III 18. Springer International Publishing (2015)
Kalman, R.E.: A new approach to linear filtering and prediction problems, pp. 35–45 (1960)
Schonberger, J.L., Frahm, J.-M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Yang, J., Pavone, M., Wang, Y.: Freenerf: improving few-shot neural rendering with free frequency regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2023)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Hu, G., Zhao, H., Huo, Q., Zhu, J., Yang, P. (2025). Multi-view 3D Reconstruction by Fusing Polarization Information. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15036. Springer, Singapore. https://doi.org/10.1007/978-981-97-8508-7_13
Download citation
DOI: https://doi.org/10.1007/978-981-97-8508-7_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-8507-0
Online ISBN: 978-981-97-8508-7
eBook Packages: Computer ScienceComputer Science (R0)