{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/coherent-reconstruction-of-multiple-humans-1","title":"Coherent Reconstruction of Multiple Humans from a Single Image","arxiv_id":"2006.08586","date":"2020-06-15","proceeding":"CVPR 2020 6","authors":["Wen Jiang","Nikos Kolotouros","Georgios Pavlakos","Xiaowei Zhou","Kostas Daniilidis"],"abstract":"In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them independently. However, this type of prediction suffers from incoherent results, e.g., interpenetration and inconsistent depth ordering between the people in the scene. Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene. To this end, a key design choice is the incorporation of the SMPL parametric body model in our top-down framework, which enables the use of two novel losses. First, a distance field-based collision loss penalizes interpenetration among the reconstructed people. Second, a depth ordering-aware loss reasons about occlusions and promotes a depth ordering of people that leads to a rendering which is consistent with the annotated instance segmentation. This provides depth supervision signals to the network, even if the image has no explicit 3D annotations. The experiments show that our approach outperforms previous methods on standard 3D pose benchmarks, while our proposed losses enable more coherent reconstruction in natural images. The project website with videos, results, and code can be found at: https://jiangwenpl.github.io/multiperson","url_abs":"https://arxiv.org/abs/2006.08586v1","url_pdf":"https://arxiv.org/pdf/2006.08586v1.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":"coherent-reconstruction-of-multiple-humans-1","repo_url":"https://github.com/JiangWenPL/multiperson","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-depth-estimation","task_name":"3D Depth Estimation"},{"task_slug":"3d-human-reconstruction","task_name":"3D Human Reconstruction"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-depth-estimation-on-relative-human","task":"3D Depth Estimation","dataset":"Relative Human","model":"CRMH","rank_in_archive_order":3,"of":3,"metrics":{"PCDR":"54.83","PCDR-Adult":"55.47","PCDR-Baby":"34.74","PCDR-Kid":"48.37","PCDR-Teen":"59.11","mPCDK":"0.781"},"uses_additional_data":true},{"leaderboard":"/sota/3d-human-reconstruction-on-agora-1","task":"3D Human Reconstruction","dataset":"AGORA","model":"PIXIE","rank_in_archive_order":2,"of":5,"metrics":{"B-MPJPE":"140.3","B-MVE":"142.2","B-NMJE":"171.1","B-NMVE":"173.4","F-MPJPE":"54.5","F-MVE":"50.2","FB-MPJPE":"189.3","FB-MVE":"191.8","FB-NMJE":"230.9","FB-NMVE":"233.9","LH/RH-MPJPE":"46.4/46.0","LH/RH-MVE":"49.5/49.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.08586","atlas_url":"https://app.syntology.ai/?focus=2006.08586","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2006.08586"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.08586\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.08586"},"call":"get_concepts_for_paper(arxiv_id=\"2006.08586\")"}],"by_repo":[{"repo":"JiangWenPL/multiperson","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"950b71e5c209a6157690be12b0fc9545774bfad11fd947611dbb42281a94744d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}