Related papers: Bridging the Reality Gap for Pose Estimation Netwo…
The performance of supervised deep learning algorithms depends significantly on the scale, quality and diversity of the data used for their training. Collecting and manually annotating large amount of data can be both time-consuming and…
RGB-based 3D hand pose estimation has been successful for decades thanks to large-scale databases and deep learning. However, the hand pose estimation network does not operate well for hand pose images whose characteristics are far…
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…
Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated…
In the industrial domain, the pose estimation of multiple texture-less shiny parts is a valuable but challenging task. In this particular scenario, it is impractical to utilize keypoints or other texture information because most of them are…
In this paper, we address the problem of camera pose estimation in outdoor and indoor scenarios. In comparison to the currently top-performing methods that rely on 2D to 3D matching, we propose a model that can directly regress the camera…
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…
Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…
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…
Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we…
In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach…
We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…
Estimating the pose of a pallet and other logistics objects is crucial for various use cases, such as automatized material handling or tracking. Innovations in computer vision, computing power, and machine learning open up new opportunities…
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…
Recently developed deep neural networks achieved state-of-the-art results in the subject of 6D object pose estimation for robot manipulation. However, those supervised deep learning methods require expensive annotated training data. Current…
Existing 3D human pose estimation methods often suffer in performance, when applied to cross-scenario inference, due to domain shifts in characteristics such as camera viewpoint, position, posture, and body size. Among these factors, camera…
Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because…
6D pose recognition has been a crucial factor in the success of robotic grasping, and recent deep learning based approaches have achieved remarkable results on benchmarks. However, their generalization capabilities in real-world…
Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…