{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-depth-from-single-monocular-images","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","arxiv_id":"1502.07411","date":"2015-02-26","proceeding":null,"authors":["Fayao Liu","Chunhua Shen","Guosheng Lin","Ian Reid"],"abstract":"In this article, we tackle the problem of depth estimation from single\nmonocular images. Compared with depth estimation using multiple images such as\nstereo depth perception, depth from monocular images is much more challenging.\nPrior work typically focuses on exploiting geometric priors or additional\nsources of information, most using hand-crafted features. Recently, there is\nmounting evidence that features from deep convolutional neural networks (CNN)\nset new records for various vision applications. On the other hand, considering\nthe continuous characteristic of the depth values, depth estimations can be\nnaturally formulated as a continuous conditional random field (CRF) learning\nproblem. Therefore, here we present a deep convolutional neural field model for\nestimating depths from single monocular images, aiming to jointly explore the\ncapacity of deep CNN and continuous CRF. In particular, we propose a deep\nstructured learning scheme which learns the unary and pairwise potentials of\ncontinuous CRF in a unified deep CNN framework. We then further propose an\nequally effective model based on fully convolutional networks and a novel\nsuperpixel pooling method, which is $\\sim 10$ times faster, to speedup the\npatch-wise convolutions in the deep model. With this more efficient model, we\nare able to design deeper networks to pursue better performance. Experiments on\nboth indoor and outdoor scene datasets demonstrate that the proposed method\noutperforms state-of-the-art depth estimation approaches.","url_abs":"http://arxiv.org/abs/1502.07411v6","url_pdf":"http://arxiv.org/pdf/1502.07411v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-depth-from-single-monocular-images","repo_url":"https://github.com/swathic5/Depth-estimation-using-neural-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"}],"methods":[{"method_slug":"crf","method_name":"CRF"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1502.07411","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}