Weakly-supervised 3D Human Pose Estimation

17 papers with code • 2 benchmarks • 2 datasets

This task targets at 3D Human Pose Estimation with fewer 3D annotation.


Use these libraries to find Weakly-supervised 3D Human Pose Estimation models and implementations
2 papers

Most implemented papers

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

DenisTome/Lifting-from-the-Deep-release CVPR 2017

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

facebookresearch/VideoPose3D CVPR 2019

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

open-mmlab/mmpose CVPR 2018

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.

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

hrhodin/UnsupervisedGeometryAwareRepresentationLearning ECCV 2018

In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations.

Heuristic Weakly Supervised 3D Human Pose Estimation

ostadabbas/hw-hup 23 May 2021

However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains.

Self-supervised Learning of Motion Capture

chingswy/HumanPoseMemo NeurIPS 2017

In this work, we propose a learning based motion capture model for single camera input.

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation

bastianwandt/RepNet CVPR 2019

This efficiently avoids a simple memorization of the training data and allows for a weakly supervised training.

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry

mkocabas/EpipolarPose CVPR 2019

Training accurate 3D human pose estimators requires large amount of 3D ground-truth data which is costly to collect.

TexturePose: Supervising Human Mesh Estimation with Texture Consistency

geopavlakos/TexturePose ICCV 2019

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 frames.

Cascaded deep monocular 3D human pose estimation with evolutionary training data

Nicholasli1995/EvoSkeleton CVPR 2020

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.