Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data

By Srinath Sridhar, Antti Oulasvirta, Christian Theobalt. 2013

288 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, 3D Vision & Pose, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In 3D Vision & Pose

In Human-Computer Interaction

Citations in the corpus

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, background): “One highly related direction is to model and estimate 3D hand joints [5,44,45,53,60,63,66,72,78,79,80,85,3] and mesh [26,27,51,55,75,83,46], object pose [14,28,29,35,43,57,64,71,76,81], or both [6,17,18,19,69].”
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals (2017, background): “Manually labeled datasets such as [31, 41] contain just a few thousand examples, making them unsuitable for large-scale training.”
Learning an efficient model of hand shape variation from depth images (2015, methodology): “This could then be used in a real time hand tracker that utilizes a detailed LBS model [22], as it is increasingly common to use a personalized shape model for hand tracking [25, 26].”
Realtime and Robust Hand Tracking from Depth (2014, methodology): “They are derived from an intuitive geometrical viewpoint, without using learning such as in [25].”
Hand Keypoint Detection in Single Images Using Multiview Bootstrapping (2017, background): “These are broadly classifiable into generative methods [14], discriminative methods [24, 25, 9, 30, 22, 27], or hybrid methods [20, 16, 18, 26, 31].”
HOnnotate: A Method for 3D Annotation of Hand and Object Poses (2019, background): “Generative approaches take advantage of a hand model and its kinematic structure to generate hand pose hypotheses that are physically plausible [12, 28, 45, 51, 53, 63, 70].”
Cross-Modal Deep Variational Hand Pose Estimation (2018, background): “More recently a number of deep-learning models have been proposed that take depth images as input and regress 2D joint locations in multiple images [24, 32] which are then used for optimization-based hand pose estimation.”
Training a Feedback Loop for Hand Pose Estimation (2015, methodology): “The runtime of our method compares favorably with other model-based methods ranging between 12 and 60 fps [19, 22, 26, 29, 37].”
Monocular Total Capture: Posing Face, Body, and Hands in the Wild (2018, unknown): “Most of previous work is based on depth image as input [40, 54, 49, 52, 65, 71].”
Two-hand Global 3D Pose Estimation using Monocular RGB (2020, methodology): “[23, 24] estimated the hand pose by using generative approach on inputs of multiple RGB cameras and a depth sensor.”
A hand pose tracking benchmark from stereo matching (2017, background): “At present, existing hand tracking datasets [2–7] are captured with active depth sensors.”
Hand Pose Estimation through Weakly-Supervised Learning of a Rich Intermediate Representation (2015, methodology): “This was adapted to hand pose estimation in [12], where an additional pose clustering step was introduced.”
GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB (2017, methodology): “One way to overcome this issue is to leverage existing multi-camera methods for tracking hand motion in 3D [41, 1, 56, 8].”
Articulated and Generalized Gaussian Kernel Correlation for Human Pose Estimation (2016, background): “On the other hand, the parametric shape representation becomes popular [12], [14]–[17], [41]–[43].”
Embodied hands (2017, methodology): “An alternative is the Sum-of-Gaussians model [Sridhar et al. 2015, 2013] (Fig.”
Real-Time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor (2017, methodology): “Free Hand Tracking : Many approaches for free hand tracking resort to multiple RGB cameras to overcome self-occlusions and achieve high accuracy [33, 1, 44].”
Depth-Based Hand Pose Estimation: Methods, Data, and Challenges (2015, unknown): “have considerably evolved, prompted by the introduction of commodity depth cameras. We believe the time Dataset Chal. Scn. Annot. Frms. Sub. Cam. Dist. (mm) ASTAR [51] A 1 435 10 ToF 270-580 Dexter 1 [42] A 1 3,157 3,157 1 Both 100-989 MSRA [33] A 1 2,400 2,400 6 ToF 339-422 ICL [45] A 1 1,599 1,599”