eprintid: 10088677 rev_number: 24 eprint_status: archive userid: 608 dir: disk0/10/08/86/77 datestamp: 2020-01-07 14:06:35 lastmod: 2021-09-20 00:21:28 status_changed: 2020-01-07 14:14:56 type: proceedings_section metadata_visibility: show creators_name: Güler, RA creators_name: Kokkinos, I title: HoloPose: Holistic 3D Human Reconstruction In-The-Wild. ispublished: inpress divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: We introduce HoloPose, a method for holistic monocular 3D human body reconstruction. We first introduce a part-based model for 3D model parameter regression that allows our method to operate in-the-wild, gracefully handling severe occlusions and large pose variation. We further train a multi-task network comprising 2D, 3D and Dense Pose estimation to drive the 3D reconstruction task. For this we introduce an iterative refinement method that aligns the model-based 3D estimates of 2D/3D joint positions and DensePose with their image-based counterparts delivered by CNNs, achieving both model-based, global consistency and high spatial accuracy thanks to the bottom-up CNN processing. We validate our contributions on challenging benchmarks, showing that our method allows us to get both accurate joint and 3D surface estimates, while operating at more than 10fps in-the-wild. More information about our approach, including videos and demos is available at http://arielai.com/holopose. date: 2019-06-20 date_type: published publisher: Computer Vision Foundation / IEEE official_url: http://openaccess.thecvf.com/CVPR2019.py oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1733490 lyricists_name: Kokkinos, Iason lyricists_id: IKOKK25 actors_name: Kokkinos, Iason actors_id: IKOKK25 actors_role: owner full_text_status: public publication: CVPR place_of_pub: Long Beach, CA, USA pagerange: 10884-10894 event_title: CVPR 2019 - IEEE Conference on Computer Vision and Pattern Recognition citation: Güler, RA; Kokkinos, I; (2019) HoloPose: Holistic 3D Human Reconstruction In-The-Wild. In: (Proceedings) CVPR 2019 - IEEE Conference on Computer Vision and Pattern Recognition. (pp. pp. 10884-10894). Computer Vision Foundation / IEEE: Long Beach, CA, USA. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10088677/1/Guler_HoloPose_Holistic_3D_Human_Reconstruction_In-The-Wild_CVPR_2019_paper.pdf