Weakly-supervised 3D Human Pose Estimation

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.

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

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

Most implemented papers archive 2025-07-28

18 shown of 18 papers with code (29 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.

• Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
  1 Jan 2017 11 repositories listed
  We 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.
• 3D human pose estimation in video with temporal convolutions and semi-supervised training
  28 Nov 2018 10 repositories listed Syntology ran 0 of 2 samples · 2 unverified · 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.
• 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.
• Heuristic Weakly Supervised 3D Human Pose Estimation
  23 May 2021 2 repositories listed
  However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains.
• Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation
  3 Apr 2018 2 repositories listed
  In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.
• A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation
  17 Mar 2024 1 repository listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  Furthermore, the pose estimator's optimization is not exposed to domain shifts, limiting its overall generalization ability.
• Automatic Labeling of Parkinson’s Disease Gait Videos with Weak Supervision
  25 Jun 2023 1 repository listed
  The method obtained state-of-the-art results on the Human3.
• AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
  22 Dec 2021 1 repository listed Syntology ran 1 of 3 samples · 2 unverified
  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.
• Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition
  19 Sep 2021 1 repository listed
  Dance 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).
• Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
  17 Aug 2021 1 repository listed
  We 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.
• MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision
  10 Aug 2021 1 repository listed
  In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date.
• PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation
  6 May 2021 1 repository listed
  To 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…
• CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
  30 Nov 2020 1 repository listed
  Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately.
• Cascaded deep monocular 3D human pose estimation with evolutionary training data
  14 Jun 2020 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  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.
• TexturePose: Supervising Human Mesh Estimation with Texture Consistency
  24 Oct 2019 1 repository listed
  Assuming 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…
• Self-Supervised Learning of 3D Human Pose using Multi-view Geometry
  6 Mar 2019 1 repository listed
  Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.
• RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation
  26 Feb 2019 1 repository listed
  This efficiently avoids a simple memorization of the training data and allows for a weakly supervised training.
• Self-supervised Learning of Motion Capture
  4 Dec 2017 1 repository listed
  In this work, we propose a learning based motion capture model for single camera input.

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. Read from the graph 2026-09-24.