Related papers: Sim2real transfer learning for 3D human pose estim…
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images…
The availability of the large-scale labeled 3D poses in the Human3.6M dataset plays an important role in advancing the algorithms for 3D human pose estimation from a still image. We observe that recent innovation in this area mainly focuses…
Estimation of 3D human pose from monocular image has gained considerable attention, as a key step to several human-centric applications. However, generalizability of human pose estimation models developed using supervision on large-scale…
Numerous fields, such as ecology, biology, and neuroscience, use animal recordings to track and measure animal behaviour. Over time, a significant volume of such data has been produced, but some computer vision techniques cannot explore it…
Synthetic data offers a compelling path to scalable pretraining when real-world data is scarce, but models pretrained on synthetic data often fail to transfer reliably to deployment settings. We study this problem in full-body human motion,…
3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose two anatomically inspired loss functions and use them with a weakly-supervised…
Estimation of human shape and pose from a single image is a challenging task. It is an even more difficult problem to map the identified human shape onto a 3D human model. Existing methods map manually labelled human pixels in real 2D…
This paper addresses the problem of monocular 3D human shape and pose estimation from an RGB image. Despite great progress in this field in terms of pose prediction accuracy, state-of-the-art methods often predict inaccurate body shapes. We…
Accurate 3D kinematics estimation of human body is crucial in various applications for human health and mobility, such as rehabilitation, injury prevention, and diagnosis, as it helps to understand the biomechanical loading experienced…
Estimating 3D human poses from 2D images is challenging due to occlusions and projective acquisition. Learning-based approaches have been largely studied to address this challenge, both in single and multi-view setups. These solutions…
In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency…
Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…
We address the problem of 3D human pose estimation from 2D input images using only weakly supervised training data. Despite showing considerable success for 2D pose estimation, the application of supervised machine learning to 3D pose…
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance,…
Estimating 3d human pose from monocular images is a challenging problem due to the variety and complexity of human poses and the inherent ambiguity in recovering depth from the single view. Recent deep learning based methods show promising…
Estimating the pose of animals can facilitate the understanding of animal motion which is fundamental in disciplines such as biomechanics, neuroscience, ethology, robotics and the entertainment industry. Human pose estimation models have…
Human pose estimation - the process of recognizing a human's limb positions and orientations in a video - has many important applications including surveillance, diagnosis of movement disorders, and computer animation. While deep learning…
Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data…
Robotic learning in simulation environments provides a faster, more scalable, and safer training methodology than learning directly with physical robots. Also, synthesizing images in a simulation environment for collecting large-scale image…
Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training datasets. This presents a fundamental problem for applications with limited,…