Browse State-of-the-Art › 3D Multi-Person Pose Estimation
3D Multi-Person Pose Estimation
35 papers with code · 5 benchmarks · 5 datasets archive 2025-07-28
This task aims to solve root-relative 3D multi-person pose estimation. No human bounding box and root joint coordinate groundtruth are used in testing time.
( Image credit: RootNet )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Shelf (1 judged, 0 placed), Panoptic (1 judged, 0 placed), Campus (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Shelf (27 rows) | RapidPoseTriangulation (with corrected labels) | RapidPoseTriangulation: Multi-view Multi-person Whole-body Human... | code | — | Compare |
| Panoptic (20 rows) | TesseTrack | TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking | — | — | Compare |
| Campus (16 rows) | TesseTrack | TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking | — | — | Compare |
| MuPoTS-3D (10 rows) | Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement | Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics... | code | — | Compare |
| AGORA (4 rows) | SPEC | SPEC: Seeing People in the Wild with an Estimated Camera | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
5 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
3 subtasks in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 62 · with a code link: 35 · where Syntology ran a sample: 14 (11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (14 of 62 tagged: 11 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 62 of 62, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
18 Dec 2017 10 repositories listedThe main objective is to minimize the reprojection loss of keypoints, which allow our model to be trained using images in-the-wild that only have ground truth 2D annotations.
-
26 Jul 2019 4 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 1 pointer-only (licence)Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
-
1 Jul 2019 4 repositories listedThe first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals.
-
14 Jan 2019 4 repositories listed Syntology 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 19 harvested samples)This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views.
-
7 Nov 2021 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regresses the multi-person 3D…
-
27 Aug 2020 2 repositories listedThrough a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
-
13 Apr 2020 2 repositories listedIn contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimations, we present an end-to-end solution which directly operates in the 3D space…
-
9 Mar 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)To further verify the scalability of our method, we propose a new large-scale multi-human dataset with 12 to 28 camera views.
-
RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond27 Mar 2025 1 repository listedThe integration of multi-view imaging and pose estimation represents a significant advance in computer vision applications, offering new possibilities for understanding human movement and interactions.
-
22 Feb 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 9 pointer-only (licence)We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image.
-
1 Jan 2024 1 repository listedA simple yet effective method for occlusion-robust 3D human mesh reconstruction from a single image is presented in this paper.
-
10 Apr 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs).
-
24 Oct 2022 1 repository listedTo tackle the challenges, we propose a coarse-to-fine pipeline that benefits from 1) inverse kinematics from the occlusion-robust 3D skeleton estimation and 2) Transformer-based relation-aware refinement techniques.
-
8 Oct 2022 1 repository listedWith the proposed body representation, we further deliver a compact single-stage multi-person pose regression network, termed as AdaptivePose.
-
22 Jul 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes.
-
20 Jul 2022 1 repository listedWhile monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked.
-
2 May 2022 1 repository listedMost of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i. e., the coordinates based on the center of the target person.
-
15 Mar 2022 1 repository listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem.
-
1 Oct 2021 1 repository listedWe then train a novel network that concatenates the camera calibration to the image features and uses these together to regress 3D body shape and pose.
-
13 Sep 2021 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 19 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified (of 22 harvested samples)Following the top-down paradigm, we decompose the task into two stages, i. e. person localization and pose estimation.
-
28 Jun 2021 1 repository listedWe present a novel method for estimation of 3D human poses from a multi-camera setup, employing distributed smart edge sensors coupled with a backend through a semantic feedback loop.
-
6 May 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance.
-
29 Apr 2021 1 repository listedAdditionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
-
17 Apr 2021 1 repository listedDespite significant progress, we show that state of the art 3D human pose and shape estimation methods remain sensitive to partial occlusion and can produce dramatically wrong predictions although much of the body is…
-
15 Apr 2021 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 2 pointer-only (licence)Second, we propose a joint-based regressor that distinguishes a target person's feature from others.
-
6 Apr 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples)Existing approaches for multi-view multi-person 3D pose estimation explicitly establish cross-view correspondences to group 2D pose detections from multiple camera views and solve for the 3D pose estimation for each…
-
5 Apr 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a…
-
24 Jan 2021 1 repository listedIn this work we propose an approach for estimating 3D human poses of multiple people from a set of calibrated cameras.
-
22 Dec 2020 1 repository listedTo tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not…
-
31 Oct 2020 1 repository listedIn multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person.
-
26 Aug 2020 1 repository listed
-
4 Aug 2020 1 repository listed
-
21 Jul 2020 1 repository listed Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 19 harvested samples)
-
28 Feb 2020 1 repository listed
-
27 Sep 2019 1 repository listed
-
11 Apr 2025 0 repositories listed
-
28 Dec 2023 0 repositories listed
-
15 Sep 2023 0 repositories listed
-
8 Feb 2023 0 repositories listed
-
Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR30 Nov 2022 0 repositories listed
-
6 Aug 2022 0 repositories listed
-
22 Jul 2022 0 repositories listed
-
22 Jul 2022 0 repositories listed
-
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation16 Jul 2022 0 repositories listed
-
25 May 2022 0 repositories listed
-
25 May 2022 0 repositories listed
-
11 Apr 2022 0 repositories listed
-
Real-time, low-cost multi-person 3D pose estimation11 Oct 2021 0 repositories listed
-
5 Oct 2021 0 repositories listed
-
23 Aug 2021 0 repositories listed
-
5 Aug 2021 0 repositories listed
-
19 Jul 2021 0 repositories listed
-
16 Jun 2021 0 repositories listed
-
1 Aug 2020 0 repositories listed
-
1 Aug 2020 0 repositories listed
-
6 Apr 2020 0 repositories listed
-
AnimePose: Multi-person 3D pose estimation and animation6 Feb 2020 0 repositories listed
-
Single-shot 3D multi-person pose estimation in complex images8 Nov 2019 0 repositories listed
-
4 Sep 2017 0 repositories listed
-
1 Oct 2016 0 repositories listed
-
6 Sep 2014 0 repositories listed
-
1 Jun 2014 0 repositories listed
Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections