Abstract
Highlights widely exist in many objects, such as the optical images of high-gloss leather, glass, plastic, metal parts, and other mirror-reflective objects. It is difficult to directly apply optical measurement techniques, such as object detection, intrinsic image decomposition, and tracking which are suitable for objects with diffuse reflection characteristics. In this paper, we proposed a specular-to-diffuse-reflection image conversion network based on improved CycleGAN to automatically remove image highlights. It does not require paired training data, and the experimental results verify the effectiveness of our method. There are two main contributions for this framework. On one hand, we proposed a confidence map based on independent average values as the initial value to solve the slow convergence problem of the network due to the lack of a strict mathematical definition for distinguishing specular reflection components from diffuse reflection components. On the other hand, we designed a logarithm-based transformation method generator which made the specular reflection and diffuse reflection components comparable. It could solve the anisotropy problem in the optimization process. This problem was caused by the fact that the peak specular reflection on the surface of a specular object was much larger than the value of the off-peak diffuse reflection. We also compared our method with the latest methods. It was found that the SSIM and PSNR values of our proposed algorithm were significantly improved, and the comparative experimental results showed that the proposed algorithm significantly improves the image conversion quality.
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
Guirong, L., Jingfan, T., Ming, J.: Research on image highlight removal based on fast bilateral filtering. Comput. Eng. Appl. 10, 176–179 (2014)
Yasuhiro, A., Okatani, T.: Separation of reflection components by sparse non-negative matrix factorization. Computer Vision–ACCV 2014: 12th Asian Conference on Computer Vision, Singapore, Singapore, November 1–5, 2014, Revised Selected Papers, Part V 12. Springer, Cham (2015)
Jie, G., Zhou, Z., Wang, L.: Single image highlight removal with a sparse and low-rank reflection model. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)
Yang, Q., Tang, J., Ahuja, N.: Efficient and robust specular highlight removal. IEEE Trans. Pattern Anal. Mach. Intell. 37(6), 1304–1311 (2014)
Duan, G., et al.: Deep inverse rendering for high-resolution SVBRDF estimation from an arbitrary number of images. ACM Trans. Graph. 38.4, 134–1 (2019)
Gang, F., et al.: A multi-task network for joint specular highlight detection and removal. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
Wu, Z., et al.: Joint specular highlight detection and removal in single images via Unet-Transformer. Comput. Visual Media 9.1, 141–154 (2023)
Wu, S., et al.: Specular-to-diffuse translation for multi-view reconstruction. In: Proceedings of the European conference on computer vision (ECCV) (2018)
Yang, J., et al.: Using deep learning to detect defects in manufacturing: a comprehensive survey and current challenges. Materials 13.24, 5755 (2020)
Tamás, C., et al.: Visual-based defect detection and classification approaches for industrial applications—a survey. Sensors 20.5, 1459 (2020)
Kahraman, Y., Durmuşoğlu, A.: Deep learning-based fabric defect detection: a review. Text. Res. J. 93(5–6), 1485–1503 (2023)
Niu, S., et al.: Defect image sample generation with GAN for improving defect recognition. IEEE Trans. Autom. Sci. Eng. 17.3, 1611–1622 (2020)
Mark, B., et al.: Nerd: neural reflectance decomposition from image collections. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2021)
Partha, D., Karaoglu, S., Gevers, T.: PIE-Net: photometric invariant edge guided network for intrinsic image decomposition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022)
Stamatios, G., et al.: Delight-net: Decomposing reflectance maps into specular materials and natural illumination. arXiv preprint arXiv:1603.08240 (2016)
Song, S., Funkhouser, T.: Neural illumination: lighting prediction for indoor environments. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019)
Li, Z., et al.: Inverse rendering for complex indoor scenes: Shape, spatially-varying lighting and svbrdf from a single image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
Guo, Z., Shao, M., Li, S.: Image-to-image translation using an offset-based multi-scale codes GAN encoder. Visual Comput. 1–17 (2023)
Chen, M., et al.: Cycle-attention-derain: unsupervised rain removal with CycleGAN. Visual Comput. 1–13 (2023)
Yi, Z., et al.: Dualgan: unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision (2017)
Kim, T., et al.: Learning to discover cross-domain relations with generative adversarial networks. In: International Conference on Machine Learning. PMLR (2017)
Zhao, Y., et al.: Joint SVBRDF Recovery and Synthesis From a Single Image using an Unsupervised Generative Adversarial Network. EGSR (DL) (2020)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Long, J., Evan, S., Trevor, D.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Huang, G., et al.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Zhang, Z., et al. “A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Trans. Med. Imag. 37.6, 1407–1417 (2018)
Wojciech, M.: A data-driven reflectance model. Diss. Massachusetts Institute of Technology (2003)
Sun, T., Jensen, H.W., Ramamoorthi, R.: Connecting measured brdfs to analytic brdfs by data-driven diffuse-specular separation. ACM Trans. Graph. (TOG) 37.6, 1–15 (2018)
Lee, H.-Y., et al.: Diverse image-to-image translation via disentangled representations. In: Proceedings of the European conference on computer vision (ECCV) (2018)
Acknowledgment
This research was made possible by the financial support of the Educational Commission of Hubei Province of China (Grant No. D20211701).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, Y. et al. (2024). Highlight Removal from a Single Image Based on a Prior Knowledge Guided Unsupervised CycleGAN. In: Sheng, B., Bi, L., Kim, J., Magnenat-Thalmann, N., Thalmann, D. (eds) Advances in Computer Graphics. CGI 2023. Lecture Notes in Computer Science, vol 14495. Springer, Cham. https://doi.org/10.1007/978-3-031-50069-5_32
Download citation
DOI: https://doi.org/10.1007/978-3-031-50069-5_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50068-8
Online ISBN: 978-3-031-50069-5
eBook Packages: Computer ScienceComputer Science (R0)