“Progressive-CRF-net: Single Image Radiometric Calibration Using Stacked CNNs” by Kao, Chen and Ouhyoung

  • ©Yi-Lung Kao, Yu-Sheng Chen, and Ming Ouhyoung

  • ©Yi-Lung Kao, Yu-Sheng Chen, and Ming Ouhyoung

Conference:


Entry Number: 15

Title:

    Progressive-CRF-net: Single Image Radiometric Calibration Using Stacked CNNs

Presenter(s):



Abstract:


    A camera is a good instrument for measuring scene radiance. However, to please the human eye, the resulting image brightness is not linear to the scene radiance, so solving the mapping function between scene radiance and image brightness is very important. We propose a Progressive-CRF-net for radiometric calibration. By stacking multiple networks and using the pre-trained weights, this approach can reduce the training time and reach better performance than that of previous work. Our experiments show a significant improvement based on PSNR and SSIM.

References:


    • Han Li and Pieter Peers. 2017. CRF-net: Single Image Radiometric Calibration using CNNs. In Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017). ACM, 5.
    • Stephen Lin, Jinwei Gu, Shuntaro Yamazaki, and Heung-Yeung Shum. 2004. Radiometric calibration from a single image. In Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, Vol. 2. IEEE, II–II.
    • Stephen Lin and Lei Zhang. 2005. Determining the radiometric response function from a single grayscale image. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, Vol. 2. IEEE, 66–73.
    • Tomoo Mitsunaga and Shree K Nayar. 1999. Radiometric self calibration. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., Vol. 1. IEEE, 374–380.
    • Tian-Tsong Ng, Shih-Fu Chang, and Mao-Pei Tsui. 2007. Using geometry invariants for camera response function estimation. In Computer Vision and Pattern Recognition, 2007. CVPR’07. IEEE Conference on. IEEE, 1–8.

Keyword(s):



Acknowledgements:


    This project was partially supported by Ministry of Science and Technology (MOST), Taiwan: No. 106-3114-E-002-012, No. 105-2221-E-002-128-MY2, and Mediatek Inc. No. MTKC-2018-0167. Thanks “Mark Fairchild’s HDR Photographic Survey” for providing high quality HDR image dataset.


PDF:



ACM Digital Library Publication:


Overview Page:



Type: