Deep Learning-Based Human Pose Estimation: A Survey

Zheng, Ce; Wu, Wenhan; Yang, Taojiannan; Zhu, Sijie; Chen, Chen; Liu, Ruixu; Shen, Ju; Kehtarnavaz, Nasser; Shah, Mubarak

doi:10.48550/arxiv.2012.13392

Cited by 54 publications

(74 citation statements)

References 294 publications

(314 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pose estimation is a classical computer vision problem with wide ranging applications (1)(2)(3)28). Pose estimation methods are evaluated on several benchmarks for 2D multi-human pose estimation, incl.…”

Section: Pose Estimationmentioning

confidence: 99%

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

Stoffl¹,

Vidal²,

Mathis³

2021

Preprint

View full text Add to dashboard Cite

We propose a new end-to-end trainable approach for multi-instance pose estimation by combining a convolutional neural network with a transformer. We cast multi-instance pose estimation from images as a direct set prediction problem. Inspired by recent work on end-to-end trainable object detection with transformers, we use a transformer encoder-decoder architecture together with a bipartite matching scheme to directly regress the pose of all individuals in a given image. Our model, called POse Estimation Transformer (POET), is trained using a novel set-based global loss that consists of a keypoint loss, a keypoint visibility loss, a center loss and a class loss. POET reasons about the relations between detected humans and the full image context to directly predict the poses in parallel. We show that POET can achieve high accuracy on the challenging COCO keypoint detection task. To the best of our knowledge, this model is the first end-to-end trainable multi-instance human pose estimation method.

show abstract

Section: Pose Estimationmentioning

confidence: 99%

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

Stoffl¹,

Vidal²,

Mathis³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Since the related work is vast, here we discuss the more relevant approaches. We direct the interested reader to a recent and extensive survey [51].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic Modeling for Human Mesh Recovery

Kolotouros¹,

Pavlakos²,

Jayaraman³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/ ˜nkolot/projects/prohmr.

show abstract

“…In recent years, deep learning has seen widespread use for inferring human pose, by using convolutional neural networks (CNNs) to encode features in an image and output some representation of human pose. We refer the reader to literature surveys for more comprehensive coverage [52], [53]. Here we discuss approaches that are relevant to the particular black-box and white-box architectures we use.…”

Section: Related Workmentioning

confidence: 99%

BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image

Clever¹,

Grady²,

Turk³

et al. 2021

Preprint

View full text Add to dashboard Cite

Contact pressure between the human body and its surroundings has important implications. For example, it plays a role in comfort, safety, posture, and health. We present a method that infers contact pressure between a human body and a mattress from a depth image. Specifically, we focus on using a depth image from a downward facing camera to infer pressure on a body at rest in bed occluded by bedding, which is directly applicable to the prevention of pressure injuries in healthcare. Our approach involves augmenting a real dataset with synthetic data generated via a soft-body physics simulation of a human body, a mattress, a pressure sensing mat, and a blanket. We introduce a novel deep network that we trained on an augmented dataset and evaluated with real data. The network contains an embedded human body mesh model and uses a white-box model of depth and pressure image generation. Our network successfully infers body pose, outperforming prior work. It also infers contact pressure across a 3D mesh model of the human body, which is a novel capability, and does so in the presence of occlusion from blankets.

show abstract

Deep Learning-Based Human Pose Estimation: A Survey

Cited by 54 publications

References 294 publications

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

Probabilistic Modeling for Human Mesh Recovery

BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Image

Contact Info

Product

Resources

About