This paper is the first to propose a deep learning approach for denoising depth images produced by Time of Flight (ToF) cameras. The noise in ToF depth images is spatially nonstationary, and depends on the strength of the infrared signal coming back to the sensor. Existing ToF denoising methods do not capture the non-stationary nature of noise in such images. We propose a fairly simple, yet efficient Convolutional Neural Network (CNN) that makes use of both the depth and infrared information to denoise ToF depth images. To train the network, a novel methodology to generate a high amount of training samples is proposed. The experimental results demonstrate that the proposed CNN-based ToF denoising method substantially outperforms the state-of-the-art denoising methods, including wavelet shrinkage, least squares optimization, Bilateral Filtering and BM3D.
Bolsée, Q & Munteanu, A 2018, Cnn-based Denoising of Time-Of-Flight Depth Images. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings: ICIP 2018., 8451610, pp. 510-514, 2018 IEEE International Conference on Image Processing (ICIP), Athens, Greece, 7/10/18. https://doi.org/10.1109/ICIP.2018.8451610
Bolsée, Q., & Munteanu, A. (2018). Cnn-based Denoising of Time-Of-Flight Depth Images. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings: ICIP 2018 (pp. 510-514). Article 8451610 https://doi.org/10.1109/ICIP.2018.8451610
@inproceedings{20e5a4aaff784b13ad0f232c5b4fba83,
title = "Cnn-based Denoising of Time-Of-Flight Depth Images",
abstract = "This paper is the first to propose a deep learning approach for denoising depth images produced by Time of Flight (ToF) cameras. The noise in ToF depth images is spatially nonstationary, and depends on the strength of the infrared signal coming back to the sensor. Existing ToF denoising methods do not capture the non-stationary nature of noise in such images. We propose a fairly simple, yet efficient Convolutional Neural Network (CNN) that makes use of both the depth and infrared information to denoise ToF depth images. To train the network, a novel methodology to generate a high amount of training samples is proposed. The experimental results demonstrate that the proposed CNN-based ToF denoising method substantially outperforms the state-of-the-art denoising methods, including wavelet shrinkage, least squares optimization, Bilateral Filtering and BM3D.",
keywords = "Convolutional Neural Network, Denoising, Residual learning, Time-of-Flight",
author = "Quentin Bols{\'e}e and Adrian Munteanu",
year = "2018",
month = oct,
day = "11",
doi = "10.1109/ICIP.2018.8451610",
language = "English",
pages = "510--514",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",
note = "2018 IEEE International Conference on Image Processing (ICIP) ; Conference date: 07-10-2018 Through 10-10-2018",
}