{"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-the-depths-of-moving-people-by","title":"Learning the Depths of Moving People by Watching Frozen People","arxiv_id":"1904.11111","date":"2019-04-25","proceeding":"CVPR 2019 6","authors":["Zhengqi Li","Tali Dekel","Forrester Cole","Richard Tucker","Noah Snavely","Ce Liu","William T. Freeman"],"abstract":"We present a method for predicting dense depth in scenarios where both a\nmonocular camera and people in the scene are freely moving. Existing methods\nfor recovering depth for dynamic, non-rigid objects from monocular video impose\nstrong assumptions on the objects' motion and may only recover sparse depth. In\nthis paper, we take a data-driven approach and learn human depth priors from a\nnew source of data: thousands of Internet videos of people imitating\nmannequins, i.e., freezing in diverse, natural poses, while a hand-held camera\ntours the scene. Because people are stationary, training data can be generated\nusing multi-view stereo reconstruction. At inference time, our method uses\nmotion parallax cues from the static areas of the scenes to guide the depth\nprediction. We demonstrate our method on real-world sequences of complex human\nactions captured by a moving hand-held camera, show improvement over\nstate-of-the-art monocular depth prediction methods, and show various 3D\neffects produced using our predicted depth.","url_abs":"http://arxiv.org/abs/1904.11111v1","url_pdf":"http://arxiv.org/pdf/1904.11111v1.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":[],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"}],"methods":[],"datasets_introduced":[{"slug":"mannequinchallenge","name":"MannequinChallenge","full_name":"MannequinChallenge"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.11111","atlas_url":"https://app.syntology.ai/?focus=1904.11111","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}