Browse State-of-the-Art › Human Mesh Recovery
Human Mesh Recovery
53 papers with code · 1 benchmark · 3 datasets archive 2025-07-28
Estimate 3D body mesh from images
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| BEDLAM (3 rows) | Multi-HMR | Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot | code | 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 | 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
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 109 · with a code link: 53 · where Syntology ran a sample: 11 (11 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 109 tagged: 11 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 109, 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.
-
1 Aug 2022 6 repositories listed Syntology community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Top-down methods dominate the field of 3D human pose and shape estimation, because they are decoupled from human detection and allow researchers to focus on the core problem.
-
21 Oct 2024 2 repositories listedThen, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model.
-
4 Dec 2023 2 repositories listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 11 unverified (of 24 harvested samples) · 11 pointer-only (licence)Human-centric perception tasks, e. g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
-
20 Nov 2023 2 repositories listedIn recent years, point cloud perception tasks have been garnering increasing attention.
-
30 Mar 2021 2 repositories listedRegression-based methods have recently shown promising results in reconstructing human meshes from monocular images.
-
20 Aug 2019 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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)Different from the existing methods try to obtain all the complex 3D pose, shape, and camera parameters from one coupling feature, we propose a skeleton-disentangling based framework, which divides this task into…
-
15 May 2025 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)To address these issues, we propose ADHMR, a framework that Aligns a Diffusion-based HMR model in a preference optimization manner.
-
8 Apr 2025 1 repository listedHuman pose and shape (HPS) estimation presents challenges in diverse scenarios such as crowded scenes, person-person interactions, and single-view reconstruction.
-
9 Jan 2025 1 repository listedTo address this issue, we develop a scalable annotation pipeline that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.
-
27 Dec 2024 1 repository listedTo address this, we propose SSR-STF, a dual-stream model that effectively integrates local features with global dependencies to enhance 3D human pose estimation.
-
25 Nov 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples)Instead, we propose to additionally supervise the learned distributions by minimizing the distance to distributions encoded in heatmaps of a 2D pose detector.
-
25 Apr 2024 1 repository listedWe address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy.
-
1 Apr 2024 1 repository listedThe recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion.
-
19 Mar 2024 1 repository listedHuman mesh recovery from arbitrary multi-view images involves two characteristics: the arbitrary camera poses and arbitrary number of camera views.
-
14 Mar 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)We present Score-Guided Human Mesh Recovery (ScoreHMR), an approach for solving inverse problems for 3D human pose and shape reconstruction.
-
29 Feb 2024 1 repository listedTo the best of our knowledge, this survey is arguably the first to comprehensively cover deep learning methods for 3D human pose estimation, including both single-person and multi-person approaches, as well as human…
-
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.
-
3 Feb 2024 1 repository listedOur key idea is that with multiple RoIs as input, we can estimate multiple local cameras and have the opportunity to design and apply additional constraints between cameras to improve the accuracy of the cameras and, in…
-
25 Jan 2024 1 repository listedIn this way, we obtain a meta-model, the meta-parameter of which is friendly to the test-time optimization.
-
3 Jan 2024 1 repository listedThis method can remarkably improve the smoothness of recovery results from video.
-
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.
-
9 Dec 2023 1 repository listedOur approach demonstrates considerable enhancements over common uniform scheduling used in image domains, boasting improvements of 5.
-
29 Nov 2023 1 repository listedOur contributions include a novel weak-supervised camera calibration technique, an effective orientation correction module, and a decoupling strategy that significantly improves the generalizability and accuracy of…
-
24 Nov 2023 1 repository listedIn this work, we propose BinaryHPE, a novel binarization method designed to estimate the 3D human body, face, and hands parameters efficiently.
-
12 Oct 2023 1 repository listedFor physical human-robot interactions (pHRI), a robot needs to estimate the accurate body pose of a target person.
-
20 Aug 2023 1 repository listed Syntology official (archive's flag): 20 ran · 20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 24 harvested samples) · 3 pointer-only (licence)Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging.
-
5 Aug 2023 1 repository listedIn contrast, we propose a generative approach framework, called "Diffusion-based Human Mesh Recovery (Diff-HMR)" that takes advantage of the denoising diffusion process to account for multiple plausible outcomes.
-
31 Jul 2023 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 14 harvested samples) · 4 pointer-only (licence)Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D&3D aligned results in a coarse-to-fine manner and a novel 3D joint contrastive learning approach for…
-
3 Jul 2023 1 repository listedIn this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset.
-
31 May 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 1 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) · 1 unverified (of 5 harvested samples)
-
12 Apr 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 2 pointer-only (licence)
-
30 Mar 2023 1 repository listed
-
23 Mar 2023 1 repository listed
-
16 Mar 2023 1 repository listed
-
10 Mar 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
28 Dec 2022 1 repository listed
-
9 Dec 2022 1 repository listed
-
21 Sep 2022 1 repository listed
-
13 Jul 2022 1 repository listed
-
21 Jun 2022 1 repository listed
-
3 Mar 2022 1 repository listed
-
2 Dec 2021 1 repository listed
-
24 Nov 2021 1 repository listed
-
18 Oct 2021 1 repository listed
-
26 Aug 2021 1 repository listed
-
15 Jul 2021 1 repository listed
-
17 Dec 2020 1 repository listed
-
31 Dec 2019 1 repository listed
-
MetricHMR: Metric Human Mesh Recovery from Monocular Images11 Jun 2025 0 repositories listed
-
SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models17 Apr 2025 0 repositories listed
-
DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery3 Apr 2025 0 repositories listed
-
Reconstructing Humans with a Biomechanically Accurate Skeleton27 Mar 2025 0 repositories listed
-
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision8 Mar 2025 0 repositories listed
-
14 Jan 2025 0 repositories listed
-
Joint Optimization for 4D Human-Scene Reconstruction in the Wild4 Jan 2025 0 repositories listed
-
ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimation3 Jan 2025 0 repositories listed
-
BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation1 Jan 2025 0 repositories listed
-
M3GYM: A Large-Scale Multimodal Multi-view Multi-person Pose Dataset for Fitness Activity Understanding in Real-world Settings1 Jan 2025 0 repositories listed
-
19 Dec 2024 0 repositories listed
-
CondiMen: Conditional Multi-Person Mesh Recovery17 Dec 2024 0 repositories listed
-
BLADE: Single-view Body Mesh Learning through Accurate Depth Estimation11 Dec 2024 0 repositories listed
-
HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery5 Dec 2024 0 repositories listed
-
Continuous-Time Human Motion Field from Events2 Dec 2024 0 repositories listed
-
DeforHMR: Vision Transformer with Deformable Cross-Attention for 3D Human Mesh Recovery18 Nov 2024 0 repositories listed
-
DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose27 Aug 2024 0 repositories listed
-
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery30 Jun 2024 0 repositories listed
-
MEGA: Masked Generative Autoencoder for Human Mesh Recovery29 May 2024 0 repositories listed
-
3D Human Scan With A Moving Event Camera12 Apr 2024 0 repositories listed
-
19 Mar 2024 0 repositories listed
-
Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery14 Mar 2024 0 repositories listed
-
Multi-Human Mesh Recovery with Transformers26 Feb 2024 0 repositories listed
-
EgoGen: An Egocentric Synthetic Data Generator16 Jan 2024 0 repositories listed
-
HardMo: A Large-Scale Hardcase Dataset for Motion Capture1 Jan 2024 0 repositories listed
-
PostureHMR: Posture Transformation for 3D Human Mesh Recovery1 Jan 2024 0 repositories listed
-
Human Body Model based ID using Shape and Pose Parameters6 Dec 2023 0 repositories listed
-
28 Nov 2023 0 repositories listed
-
Cross-view and Cross-pose Completion for 3D Human Understanding15 Nov 2023 0 repositories listed
-
Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing28 Sep 2023 0 repositories listed
-
Distribution-Aligned Diffusion for Human Mesh Recovery25 Aug 2023 0 repositories listed
-
Learning Dense UV Completion for Human Mesh Recovery20 Jul 2023 0 repositories listed
-
30 Jun 2023 0 repositories listed
-
D3L: Decomposition of 3D Rotation and Lift from 2D Joint to 3D for Human Mesh Recovery10 Jun 2023 0 repositories listed
-
Learning Human Mesh Recovery in 3D Scenes6 Jun 2023 0 repositories listed
-
23 Mar 2023 0 repositories listed
-
Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery15 Jan 2023 0 repositories listed
-
NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action1 Jan 2023 0 repositories listed
-
Progressive Multi-view Human Mesh Recovery with Self-Supervision10 Dec 2022 0 repositories listed
-
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer19 Nov 2022 0 repositories listed
-
Multi-view Human Body Mesh Translator4 Oct 2022 0 repositories listed
-
Self-supervised Human Mesh Recovery with Cross-Representation Alignment10 Sep 2022 0 repositories listed
-
Occluded Human Mesh Recovery24 Mar 2022 0 repositories listed
-
SMPL-A: Modeling Person-Specific Deformable Anatomy1 Jan 2022 0 repositories listed
-
VoteHMR: Occlusion-Aware Voting Network for Robust 3D Human Mesh Recovery from Partial Point Clouds17 Oct 2021 0 repositories listed
-
27 Jul 2021 0 repositories listed
-
13 Jul 2021 0 repositories listed
Syntology lines on 11 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