Open AccessPosted Content
How Robust is 3D Human Pose Estimation to Occlusion
Reads0
Chats0
TLDR
This work takes a first step in improving occlusion-robustness through training data augmentation with synthetic occlusions and turns out to be an effective regularizer that is beneficial even for non-occluded test cases.Abstract:
Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks. This leaves the question open: how robust are state-of-the-art 3D pose estimation methods against partial occlusions? We study several types of synthetic occlusions over the Human3.6M dataset and find a method with state-of-the-art benchmark performance to be sensitive even to low amounts of occlusion. Addressing this issue is key to progress in applications such as collaborative and service robotics. We take a first step in this direction by improving occlusion-robustness through training data augmentation with synthetic occlusions. This also turns out to be an effective regularizer that is beneficial even for non-occluded test cases.read more
Citations
More filters
Proceedings ArticleDOI
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry
TL;DR: In this article, a self-supervised learning method for 3D human pose estimation is proposed, which does not need any 3D ground-truth data or camera extrinsics.
Proceedings Article
Sim2real transfer learning for 3D human pose estimation: motion to the rescue
Carl Doersch,Andrew Zisserman +1 more
TL;DR: This paper shows that standard neural-network approaches, which perform poorly when trained on synthetic RGB images, can perform well when the data is pre-processed to extract cues about the person’s motion, notably as optical flow and the motion of 2D keypoints.
Posted Content
Exploiting temporal context for 3D human pose estimation in the wild
TL;DR: In this paper, a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos is presented, where reconstructing a person over an entire sequence gives extra constraints that can resolve ambiguities.
Proceedings ArticleDOI
Object-Occluded Human Shape and Pose Estimation From a Single Color Image
TL;DR: This paper proposes a novel two-branch network architecture to train an end-to-end regressor via the latent feature supervision, which also includes a novel saliency map sub-net to extract the human information from object-occluded color images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Book ChapterDOI
Stacked Hourglass Networks for Human Pose Estimation
TL;DR: This work introduces a novel convolutional network architecture for the task of human pose estimation that is described as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions.
Posted Content
Improved Regularization of Convolutional Neural Networks with Cutout.
TL;DR: This paper shows that the simple regularization technique of randomly masking out square regions of input during training, which is called cutout, can be used to improve the robustness and overall performance of convolutional neural networks.
Posted Content
Stacked Hourglass Networks for Human Pose Estimation
TL;DR: Stacked hourglass networks as mentioned in this paper were proposed for human pose estimation, where features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body, and repeated bottom-up, top-down processing with intermediate supervision is critical to improving the performance of the network.