3D Multi-Person Pose Estimation

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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 35 papers with code (62 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• End-to-end Recovery of Human Shape and Pose
  18 Dec 2017 10 repositories listed
  The 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.
• Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
  26 Jul 2019 4 repositories listed Syntology ran 1 of 7 samples · 6 unverified
  Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
• XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
  1 Jul 2019 4 repositories listed
  The 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.
• Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
  14 Jan 2019 4 repositories listed Syntology ran 2 of 19 samples · 17 unverified
  This paper addresses the problem of 3D pose estimation for multiple people in a few calibrated camera views.
• Direct Multi-view Multi-person 3D Pose Estimation
  7 Nov 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  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…
• Monocular, One-stage, Regression of Multiple 3D People
  27 Aug 2020 2 repositories listed
  Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map.
• VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
  13 Apr 2020 2 repositories listed
  In 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 $3$D space,…
• Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS
  9 Mar 2020 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 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 Millisecond
  27 Mar 2025 1 repository listed
  The 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.
• Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
  22 Feb 2024 1 repository listed Syntology ran 8 of 9 samples · 1 unverified · 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.
• Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction
  1 Jan 2024 1 repository listed
  A simple yet effective method for occlusion-robust 3D human mesh reconstruction from a single image is presented in this paper.
• Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild
  10 Apr 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 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).
• Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement
  24 Oct 2022 1 repository listed
  To 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.
• AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regression
  8 Oct 2022 1 repository listed
  With the proposed body representation, we further deliver a compact single-stage multi-person pose regression network, termed as AdaptivePose.
• Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
  22 Jul 2022 1 repository listed Syntology ran 0 of 4 samples · 4 unverified · 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.
• VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
  20 Jul 2022 1 repository listed
  While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked.
• Dual networks based 3D Multi-Person Pose Estimation from Monocular Video
  2 May 2022 1 repository listed
  Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.
• Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
  15 Mar 2022 1 repository listed Syntology ran 1 of 3 samples · 2 unverified
  In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem.
• SPEC: Seeing People in the Wild with an Estimated Camera
  1 Oct 2021 1 repository listed
  We 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.
• Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
  13 Sep 2021 1 repository listed Syntology ran 19 of 22 samples · 3 unverified
  Following the top-down paradigm, we decompose the task into two stages, i.
• Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
  28 Jun 2021 1 repository listed
  We 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.
• Body Meshes as Points
  6 May 2021 1 repository listed Syntology ran 1 of 7 samples · 6 unverified
  In this work, we present a single-stage model, Body Meshes as Points (BMP), to simplify the pipeline and lift both efficiency and performance.
• AGORA: Avatars in Geography Optimized for Regression Analysis
  29 Apr 2021 1 repository listed
  Additionally, we fine-tune methods on AGORA and show improved performance on both AGORA and 3DPW, confirming the realism of the dataset.
• PARE: Part Attention Regressor for 3D Human Body Estimation
  17 Apr 2021 1 repository listed
  Despite 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…
• Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
  15 Apr 2021 1 repository listed Syntology ran 3 of 9 samples · 6 unverified
  Second, we propose a joint-based regressor that distinguishes a target person's feature from others.
• Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
  6 Apr 2021 1 repository listed Syntology ran 6 of 9 samples · 3 unverified
  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…
• Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
  5 Apr 2021 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  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…
• Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views
  24 Jan 2021 1 repository listed
  In this work we propose an approach for estimating 3D human poses of multiple people from a set of calibrated cameras.
• Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos
  22 Dec 2020 1 repository listed
  To 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…
• Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People
  31 Oct 2020 1 repository listed
  In multi-person pose estimation actors can be heavily occluded, even become fully invisible behind another person.

Syntology lines on 13 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. Read from the graph 2026-09-24.