{"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/v2v-posenet-voxel-to-voxel-prediction-network","title":"V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map","arxiv_id":"1711.07399","date":"2017-11-20","proceeding":"CVPR 2018 6","authors":["Gyeongsik Moon","Ju Yong Chang","Kyoung Mu Lee"],"abstract":"Most of the existing deep learning-based methods for 3D hand and human pose\nestimation from a single depth map are based on a common framework that takes a\n2D depth map and directly regresses the 3D coordinates of keypoints, such as\nhand or human body joints, via 2D convolutional neural networks (CNNs). The\nfirst weakness of this approach is the presence of perspective distortion in\nthe 2D depth map. While the depth map is intrinsically 3D data, many previous\nmethods treat depth maps as 2D images that can distort the shape of the actual\nobject through projection from 3D to 2D space. This compels the network to\nperform perspective distortion-invariant estimation. The second weakness of the\nconventional approach is that directly regressing 3D coordinates from a 2D\nimage is a highly non-linear mapping, which causes difficulty in the learning\nprocedure. To overcome these weaknesses, we firstly cast the 3D hand and human\npose estimation problem from a single depth map into a voxel-to-voxel\nprediction that uses a 3D voxelized grid and estimates the per-voxel likelihood\nfor each keypoint. We design our model as a 3D CNN that provides accurate\nestimates while running in real-time. Our system outperforms previous methods\nin almost all publicly available 3D hand and human pose estimation datasets and\nplaced first in the HANDS 2017 frame-based 3D hand pose estimation challenge.\nThe code is available in https://github.com/mks0601/V2V-PoseNet_RELEASE.","url_abs":"http://arxiv.org/abs/1711.07399v3","url_pdf":"http://arxiv.org/pdf/1711.07399v3.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":"v2v-posenet-voxel-to-voxel-prediction-network","repo_url":"https://github.com/mks0601/V2V-PoseNet_RELEASE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"v2v-posenet-voxel-to-voxel-prediction-network","repo_url":"https://github.com/Neilblaze/Aerowave","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"v2v-posenet-voxel-to-voxel-prediction-network","repo_url":"https://github.com/YangYangTaoTao/V2V-PoseNet_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"v2v-posenet-voxel-to-voxel-prediction-network","repo_url":"https://github.com/dragonbook/V2V-PoseNet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"v2v-posenet-voxel-to-voxel-prediction-network","repo_url":"https://github.com/rajbharat/PoseNet-V2V-Pytorch1.0-Win10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-hand-pose-estimation","task_name":"3D Hand Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"hand-pose-estimation","task_name":"Hand Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hand-pose-estimation-on-hands-2017","task":"Hand Pose Estimation","dataset":"HANDS 2017","model":"V2V-PoseNet","rank_in_archive_order":4,"of":9,"metrics":{"Average 3D Error":"9.95"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-icvl-hands","task":"Hand Pose Estimation","dataset":"ICVL Hands","model":"V2V-PoseNet","rank_in_archive_order":8,"of":15,"metrics":{"Average 3D Error":"6.28"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-msra-hands","task":"Hand Pose Estimation","dataset":"MSRA Hands","model":"V2V-PoseNet","rank_in_archive_order":6,"of":11,"metrics":{"Average 3D Error":"7.49"},"uses_additional_data":false},{"leaderboard":"/sota/hand-pose-estimation-on-nyu-hands","task":"Hand Pose Estimation","dataset":"NYU Hands","model":"V2V-PoseNet","rank_in_archive_order":6,"of":17,"metrics":{"Average 3D Error":"8.42"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-itop-front-view","task":"Pose Estimation","dataset":"ITOP front-view","model":"V2V-PoseNet","rank_in_archive_order":4,"of":7,"metrics":{"Mean mAP":"88.74"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-itop-top-view","task":"Pose Estimation","dataset":"ITOP top-view","model":"V2V-PoseNet","rank_in_archive_order":3,"of":5,"metrics":{"Mean mAP":"83.44"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.07399","atlas_url":"https://app.syntology.ai/?focus=1711.07399","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":"1711.07399"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.07399\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.07399"},"call":"get_concepts_for_paper(arxiv_id=\"1711.07399\")"}],"by_repo":[{"repo":"mks0601/V2V-PoseNet_RELEASE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Neilblaze/Aerowave","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"YangYangTaoTao/V2V-PoseNet_Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dragonbook/V2V-PoseNet-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"rajbharat/PoseNet-V2V-Pytorch1.0-Win10","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":"4915c79406f06df2b37bd980ce1ca77927afa68581d00e2eaffa702e3f75bf37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}