Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation. Dai, Q., Li, F., Cossairt, O., & Katsaggelos, A. K. IEEE Transactions on Computational Imaging, 8:224–235, IEEE, 2022. ![Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Dense depth map capture is challenging in existing active sparse illumination based depth acquisition techniques, such as LiDAR. Various techniques have been proposed to estimate a dense depth map based on fusion of the sparse depth map measurement with the RGB image. Recent advances in hardware enable adaptive depth measurements resulting in further improvement of the dense depth map estimation. In this paper, we study the topic of estimating dense depth from depth sampling. The adaptive sparse depth sampling network is jointly trained with a fusion network of an RGB image and sparse depth, to generate optimal adaptive sampling masks. Deep learning based superpixel sampling and soft sampling approximation are applied. We show that such adaptive sampling masks can generalize well to many RGB and sparse depth fusion algorithms under a variety of sampling rates (as low as 0.0625%). The proposed adaptive sampling method is fully differentiable and flexible to be trained end-to-end with upstream perception algorithms.
@article{dai2022adaptive,
abstract = {Dense depth map capture is challenging in existing active sparse illumination based depth acquisition techniques, such as LiDAR. Various techniques have been proposed to estimate a dense depth map based on fusion of the sparse depth map measurement with the RGB image. Recent advances in hardware enable adaptive depth measurements resulting in further improvement of the dense depth map estimation. In this paper, we study the topic of estimating dense depth from depth sampling. The adaptive sparse depth sampling network is jointly trained with a fusion network of an RGB image and sparse depth, to generate optimal adaptive sampling masks. Deep learning based superpixel sampling and soft sampling approximation are applied. We show that such adaptive sampling masks can generalize well to many RGB and sparse depth fusion algorithms under a variety of sampling rates (as low as 0.0625%). The proposed adaptive sampling method is fully differentiable and flexible to be trained end-to-end with upstream perception algorithms.},
author = {Dai, Qiqin and Li, Fengqiang and Cossairt, Oliver and Katsaggelos, Aggelos K.},
doi = {10.1109/TCI.2022.3155377},
issn = {2333-9403},
journal = {IEEE Transactions on Computational Imaging},
keywords = {Adaptive sampling,Deep learning,Depth estimation,Sensor fusion},
pages = {224--235},
publisher = {IEEE},
title = {{Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation}},
url = {https://ieeexplore.ieee.org/document/9723580/},
volume = {8},
year = {2022}
}
Downloads: 0
{"_id":"YN8cykpa9ZsPrxP6b","bibbaseid":"dai-li-cossairt-katsaggelos-adaptiveilluminationbaseddepthsensingusingdeepsuperpixelandsoftsamplingapproximation-2022","author_short":["Dai, Q.","Li, F.","Cossairt, O.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"Dense depth map capture is challenging in existing active sparse illumination based depth acquisition techniques, such as LiDAR. Various techniques have been proposed to estimate a dense depth map based on fusion of the sparse depth map measurement with the RGB image. Recent advances in hardware enable adaptive depth measurements resulting in further improvement of the dense depth map estimation. In this paper, we study the topic of estimating dense depth from depth sampling. The adaptive sparse depth sampling network is jointly trained with a fusion network of an RGB image and sparse depth, to generate optimal adaptive sampling masks. Deep learning based superpixel sampling and soft sampling approximation are applied. We show that such adaptive sampling masks can generalize well to many RGB and sparse depth fusion algorithms under a variety of sampling rates (as low as 0.0625%). The proposed adaptive sampling method is fully differentiable and flexible to be trained end-to-end with upstream perception algorithms.","author":[{"propositions":[],"lastnames":["Dai"],"firstnames":["Qiqin"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Fengqiang"],"suffixes":[]},{"propositions":[],"lastnames":["Cossairt"],"firstnames":["Oliver"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.1109/TCI.2022.3155377","issn":"2333-9403","journal":"IEEE Transactions on Computational Imaging","keywords":"Adaptive sampling,Deep learning,Depth estimation,Sensor fusion","pages":"224–235","publisher":"IEEE","title":"Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation","url":"https://ieeexplore.ieee.org/document/9723580/","volume":"8","year":"2022","bibtex":"@article{dai2022adaptive,\nabstract = {Dense depth map capture is challenging in existing active sparse illumination based depth acquisition techniques, such as LiDAR. Various techniques have been proposed to estimate a dense depth map based on fusion of the sparse depth map measurement with the RGB image. Recent advances in hardware enable adaptive depth measurements resulting in further improvement of the dense depth map estimation. In this paper, we study the topic of estimating dense depth from depth sampling. The adaptive sparse depth sampling network is jointly trained with a fusion network of an RGB image and sparse depth, to generate optimal adaptive sampling masks. Deep learning based superpixel sampling and soft sampling approximation are applied. We show that such adaptive sampling masks can generalize well to many RGB and sparse depth fusion algorithms under a variety of sampling rates (as low as 0.0625%). The proposed adaptive sampling method is fully differentiable and flexible to be trained end-to-end with upstream perception algorithms.},\nauthor = {Dai, Qiqin and Li, Fengqiang and Cossairt, Oliver and Katsaggelos, Aggelos K.},\ndoi = {10.1109/TCI.2022.3155377},\nissn = {2333-9403},\njournal = {IEEE Transactions on Computational Imaging},\nkeywords = {Adaptive sampling,Deep learning,Depth estimation,Sensor fusion},\npages = {224--235},\npublisher = {IEEE},\ntitle = {{Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation}},\nurl = {https://ieeexplore.ieee.org/document/9723580/},\nvolume = {8},\nyear = {2022}\n}\n","author_short":["Dai, Q.","Li, F.","Cossairt, O.","Katsaggelos, A. K."],"key":"dai2022adaptive","id":"dai2022adaptive","bibbaseid":"dai-li-cossairt-katsaggelos-adaptiveilluminationbaseddepthsensingusingdeepsuperpixelandsoftsamplingapproximation-2022","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/9723580/"},"keyword":["Adaptive sampling","Deep learning","Depth estimation","Sensor fusion"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["adaptive sampling","deep learning","depth estimation","sensor fusion"],"search_terms":["adaptive","illumination","based","depth","sensing","using","deep","superpixel","soft","sampling","approximation","dai","li","cossairt","katsaggelos"],"title":"Adaptive Illumination Based Depth Sensing Using Deep Superpixel and Soft Sampling Approximation","year":2022}