{"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/deep-autoencoder-for-combined-human-pose","title":"Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling","arxiv_id":"1807.01511","date":"2018-07-04","proceeding":"ECCV 2018 9","authors":["Matthew Trumble","Andrew Gilbert","Adrian Hilton","John Collomosse"],"abstract":"We present a method for simultaneously estimating 3D human pose and body\nshape from a sparse set of wide-baseline camera views. We train a symmetric\nconvolutional autoencoder with a dual loss that enforces learning of a latent\nrepresentation that encodes skeletal joint positions, and at the same time\nlearns a deep representation of volumetric body shape. We harness the latter to\nup-scale input volumetric data by a factor of $4 \\times$, whilst recovering a\n3D estimate of joint positions with equal or greater accuracy than the state of\nthe art. Inference runs in real-time (25 fps) and has the potential for passive\nhuman behaviour monitoring where there is a requirement for high fidelity\nestimation of human body shape and pose.","url_abs":"http://arxiv.org/abs/1807.01511v1","url_pdf":"http://arxiv.org/pdf/1807.01511v1.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":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-total-capture","task":"3D Human Pose Estimation","dataset":"Total Capture","model":"AutoEnc","rank_in_archive_order":9,"of":14,"metrics":{"Average MPJPE (mm)":"35"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.01511","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}