{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T08:03:26Z","timestamp":1762761806765,"version":"3.40.5"},"reference-count":61,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,6,17]],"date-time":"2021-06-17T00:00:00Z","timestamp":1623888000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Robotics"],"published-print":{"date-parts":[[2021,6,17]]},"abstract":"<jats:p>This paper proposes a method for monocular underwater depth estimation, which is an open problem in robotics and computer vision. To this end, we leverage publicly available in-air RGB-D image pairs for underwater depth estimation in the spherical domain with an unsupervised approach. For this, the in-air images are style-transferred to the underwater style as the first step. Given those synthetic underwater images and their ground truth depth, we then train a network to estimate the depth. This way, our learning model is designed to obtain the depth up to scale, without the need of corresponding ground truth underwater depth data, which is typically not available. We test our approach on style-transferred in-air images as well as on our own real underwater dataset, for which we computed sparse ground truth depths data via stereopsis. This dataset is provided for download. Experiments with this data against a state-of-the-art in-air network as well as different artificial inputs show that the style transfer as well as the depth estimation exhibit promising performance.<\/jats:p>","DOI":"10.1155\/2021\/6644986","type":"journal-article","created":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T19:35:05Z","timestamp":1624044905000},"page":"1-12","source":"Crossref","is-referenced-by-count":7,"title":["Underwater Depth Estimation for Spherical Images"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9988-5491","authenticated-orcid":true,"given":"Jiadi","family":"Cui","sequence":"first","affiliation":[{"name":"Mobile Autonomous Robotic Systems Lab, School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Jin","sequence":"additional","affiliation":[{"name":"Mobile Autonomous Robotic Systems Lab, School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haofei","family":"Kuang","sequence":"additional","affiliation":[{"name":"Mobile Autonomous Robotic Systems Lab, School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingwen","family":"Xu","sequence":"additional","affiliation":[{"name":"Mobile Autonomous Robotic Systems Lab, School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2879-1636","authenticated-orcid":true,"given":"S\u00f6ren","family":"Schwertfeger","sequence":"additional","affiliation":[{"name":"Mobile Autonomous Robotic Systems Lab, School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"author":"A. Gomez Chavez","key":"1","article-title":"Adaptive navigation scheme for optimal deep-sea localization using multimodal perception cues"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1163\/156855301317033595"},{"first-page":"4418","article-title":"3d reconstruction of underwater structures","author":"C. Beall","key":"3"},{"key":"4","first-page":"387","article-title":"Unsupervised generative network to enable real-time color correction of monocular underwater images","author":"J. Li","year":"2017","journal-title":"IEEE Robotics and Automation Letters (RA-L)"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/mcg.2016.26"},{"first-page":"1","article-title":"Underwater image haze removal with an underwater-ready dark channel prior","author":"T. \u0141uczy\u0144ski","key":"6"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2010.168"},{"first-page":"4282","article-title":"Maximum likelihood mapping with spectral image registration","author":"M. Pfingsthorn","key":"8"},{"first-page":"4952","article-title":"Single underwater image enhancement using depth estimation based on blurriness","author":"Y.-T. Peng","key":"9"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1007\/s10404-014-1434-7"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-017-3819-0"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-005-0603-7"},{"volume-title":"Panoramic Vision","year":"2000","author":"R. Benosman","key":"13"},{"article-title":"Pose estimation for omni-directional cameras using sinusoid fitting","author":"H. Kuang","key":"14","doi-asserted-by":"crossref","DOI":"10.1109\/IROS40897.2019.8968087"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20175"},{"author":"Q. Xu","key":"16","article-title":"Improved fourier mellin invariant for robust rotation estimation with omni-cameras"},{"first-page":"214","article-title":"Dove: dolphin omni-directional video equipment","author":"B. Terry","key":"17"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.3390\/s150306033"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2011.02.009"},{"article-title":"Joint 2d-3d-semantic data for indoor scene understanding","year":"2017","author":"I. Armeni","key":"20"},{"author":"J.-Y. Zhu","key":"21","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks"},{"article-title":"Depth estimation on underwater omni-directional images using a deep neural network","year":"2019","author":"H. Kuang","key":"22"},{"first-page":"1422","article-title":"Unsupervised visual representation learning by context prediction","author":"C. Doersch","key":"23"},{"article-title":"Adversarial feature learning","year":"2016","author":"J. Donahue","key":"24"},{"issue":"9","key":"25","doi-asserted-by":"crossref","first-page":"1734","DOI":"10.1109\/TPAMI.2015.2496141","article-title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","volume":"38","author":"A Dosovitskiy","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"author":"S. Gidaris","key":"26","article-title":"Unsupervised representation learning by predicting image rotations"},{"first-page":"649","article-title":"Colorful image colorization","author":"R. Zhang","key":"27"},{"first-page":"391","article-title":"Tracking emerges by colorizing videos","author":"C. Vondrick","key":"28"},{"first-page":"2794","article-title":"Unsupervised learning of visual representations using videos","author":"X. Wang","key":"29"},{"author":"E. Jang","key":"30","article-title":"Grasp2vec: learning object representations from self-supervised grasping"},{"author":"A. Nair","key":"31","article-title":"Contextual imagined goals for self-supervised robotic learning"},{"author":"X. Zhi","key":"32","article-title":"Learning autonomous exploration and mapping with semantic vision"},{"first-page":"270","article-title":"Unsupervised monocular depth estimation with left-right consistency","author":"C. Godard","key":"33"},{"first-page":"4811","article-title":"Self-supervised learning for single view depth and surface normal estimation","author":"H. Zhan","key":"34"},{"first-page":"3288","article-title":"Self-supervised sparse-to-dense: self-supervised depth completion from lidar and monocular camera","author":"F. Ma","key":"35"},{"first-page":"5644","article-title":"Bilateral cyclic constraint and adaptive regularization for unsupervised monocular depth prediction","author":"A. Wong","key":"36"},{"first-page":"1851","article-title":"Unsupervised learning of depth and ego-motion from video","author":"T. Zhou","key":"37"},{"first-page":"3828","article-title":"Digging into self-supervised monocular depth estimation","author":"C. Godard","key":"38"},{"first-page":"340","article-title":"Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction","author":"H. Zhan","key":"39"},{"article-title":"Visual odometry revisited: what should be learnt?","year":"2019","author":"H. Zhan","key":"40"},{"first-page":"2624","article-title":"Towards scene understanding: unsupervised monocular depth estimation with semantic-aware representation","author":"P.-Y. Chen","key":"41"},{"first-page":"1983","article-title":"Geonet: unsupervised learning of dense depth, optical flow and camera pose","author":"Z. Yin","key":"42"},{"first-page":"12240","article-title":"Competitive collaboration: joint unsupervised learning of depth, camera motion, optical flow and motion segmentation","author":"A. Ranjan","key":"43"},{"first-page":"624","article-title":"Unsupervised single image underwater depth estimation","author":"H. Gupta","key":"44"},{"first-page":"825","article-title":"Transmission estimation in underwater single images","author":"D. Paul","key":"45"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2017.2663846"},{"first-page":"1","article-title":"Underwater image dehaze using scene depth estimation with adaptive color correction","author":"X. Ding","key":"47"},{"first-page":"695","article-title":"Color transfer for underwater dehazing and depth estimation","author":"C. O Ancuti","key":"48"},{"first-page":"5140","article-title":"Automatic color correction for 3d reconstruction of underwater scenes","author":"K. A. Skinner","key":"49"},{"key":"50","doi-asserted-by":"publisher","DOI":"10.1109\/48.50695"},{"issue":"2","key":"51","article-title":"Computer analysis and simulation of underwater camera system performance","volume":"75","author":"B. L. McGlamery","year":"1975","journal-title":"SIO Reference"},{"first-page":"7947","article-title":"Unsupervised learning for depth estimation and color correction of underwater stereo imagery","author":"K. A. Skinner","key":"52"},{"first-page":"239","article-title":"Deeper depth prediction with fully convolutional residual networks","author":"I. Laina","key":"53"},{"first-page":"707","article-title":"Distortion-aware convolutional filters for dense prediction in panoramic images","author":"K. Tateno","key":"54"},{"key":"55","first-page":"2672","article-title":"Generative adversarial nets","author":"I. Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"56","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"D. Eigen","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"first-page":"889","article-title":"Geometric structure based and regularized depth estimation from 360 indoor imagery","author":"L. Jin","key":"57"},{"first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"O. Ronneberger","key":"58"},{"first-page":"488","article-title":"Saliency detection in 360 videos","author":"Z. Zhang","key":"59"},{"first-page":"789","article-title":"A minimal solution for relative pose with unknown focal length","author":"H. Stewenius","key":"60"},{"volume-title":"Multiple View Geometry in Computer Vision","year":"2003","author":"R. Hartley","key":"61"}],"container-title":["Journal of Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/6644986.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/6644986.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jr\/2021\/6644986.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T19:35:11Z","timestamp":1624044911000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/jr\/2021\/6644986\/"}},"subtitle":[],"editor":[{"given":"L.","family":"Fortuna","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,6,17]]},"references-count":61,"alternative-id":["6644986","6644986"],"URL":"https:\/\/doi.org\/10.1155\/2021\/6644986","relation":{},"ISSN":["1687-9619","1687-9600"],"issn-type":[{"type":"electronic","value":"1687-9619"},{"type":"print","value":"1687-9600"}],"subject":[],"published":{"date-parts":[[2021,6,17]]}}}