Browse State-of-the-Art › Weakly-supervised 3D Human Pose Estimation
Weakly-supervised 3D Human Pose Estimation
18 papers with code · 2 benchmarks · 2 datasets archive 2025-07-28
This task targets at 3D Human Pose Estimation with fewer 3D annotation.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 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 |
|---|---|---|---|---|---|
| Human3.6M (33 rows) | AdaptPose | AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation... | code | Syntology official (archive's flag): 3 ran · 3 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; 0 where Syntology's instrument failed) · 0 unverified | Compare |
| MPI-INF-3DHP (3 rows) | GeoRep (semi-supervised) | Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild | — | — | 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
2 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.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 29 · with a code link: 18 · where Syntology ran a sample: 3 (1 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 29 tagged: 1 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 29 of 29, 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.
-
1 Jan 2017 11 repositories listedWe propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks.
-
28 Nov 2018 10 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints.
-
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.
-
23 May 2021 2 repositories listedHowever, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains.
-
3 Apr 2018 2 repositories listedIn this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.
-
17 Mar 2024 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) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability.
-
25 Jun 2023 1 repository listedThe method obtained state-of-the-art results on the Human3.
-
22 Dec 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator.
-
19 Sep 2021 1 repository listedDance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dance genre).
-
17 Aug 2021 1 repository listedWe present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view.
-
10 Aug 2021 1 repository listedIn the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date.
-
6 May 2021 1 repository listedTo address this problem, we present PoseAug, a new auto-augmentation framework that learns to augment the available training poses towards a greater diversity and thus improve generalization of the trained 2D-to-3D pose…
-
30 Nov 2020 1 repository listedHuman pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately.
-
14 Jun 2020 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)End-to-end deep representation learning has achieved remarkable accuracy for monocular 3D human pose estimation, yet these models may fail for unseen poses with limited and fixed training data.
-
24 Oct 2019 1 repository listedAssuming that the texture of the person does not change dramatically between frames, we can apply a novel texture consistency loss, which enforces that each point in the texture map has the same texture value across all…
-
6 Mar 2019 1 repository listedTraining accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
-
26 Feb 2019 1 repository listedThis efficiently avoids a simple memorization of the training data and allows for a weakly supervised training.
-
4 Dec 2017 1 repository listedIn this work, we propose a learning based motion capture model for single camera input.
-
5 Apr 2022 0 repositories listedAvailable 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision.
-
29 Mar 2022 0 repositories listedSupervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant.
-
29 Mar 2022 0 repositories listedThe advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations.
-
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network23 May 2021 0 repositories listedAlthough monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity.
-
14 May 2021 0 repositories listedEstimating 3D human poses from video is a challenging problem.
-
Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation23 Oct 2020 0 repositories listedThe current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods.
-
9 Apr 2020 0 repositories listedCamera captured human pose is an outcome of several sources of variation.
-
17 Mar 2020 0 repositories listedOne major challenge for monocular 3D human pose estimation in-the-wild is the acquisition of training data that contains unconstrained images annotated with accurate 3D poses.
-
1 Oct 2019 0 repositories listedThe premise of training an accurate 3D human pose estimation network is the possession of huge amount of richly annotated training data.
-
18 Aug 2019 0 repositories listedWe propose to learn a 3D pose estimator by distilling knowledge from Non-Rigid Structure from Motion (NRSfM).
-
16 Apr 2017 0 repositories listedRecent advances with Convolutional Networks (ConvNets) have shifted the bottleneck for many computer vision tasks to annotated data collection.
Syntology lines on 4 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