Estimating 3D hand pose from a cluttered image

By Vassilis Athitsos, Stan Sclaroff. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings., 2003

495 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/0b9213651d939b8195b0f4225fe409af6459effb

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 Human-Computer Interaction

Citations in the corpus

Learning to Estimate 3D Hand Pose from Single RGB Images (2017, methodology): “Previous approaches differ because they rely on depth data [22, 27, 12, 13], they use explicit models to infer pose by matching against a predefined database of poses [4], or they only perform tracking based on an initial pose rather than full pose estimation [14, 18].”
Hands in action: real-time 3D reconstruction of hands in interaction with objects (2010, background): “Methods of type B) are usually nonparametric [5], [6].”
Full DOF tracking of a hand interacting with an object by modeling occlusions and physical constraints (2011, methodology): “Appearance-based methods estimate hand configurations by establishing a direct mapping of image features to the hand configuration space [3, 22, 28, 20].”
Realtime and Robust Hand Tracking from Depth (2014, unknown): “The global techniques [3] [4] search a large parameter space to avoid poor local optima, but the result is usually coarse and the search is slow.”
Fast pose estimation with parameter-sensitive hashing (2003, methodology): “Finally, in [1] a hand image was matched to a large database of rendered forms, using a sophisticated similarity measure on image features.”
Hand Pose Estimation via Latent 2.5D Heatmap Regression (2018, methodology): “These methods follow a non-parametric approach and formulate 3D pose estimation as a nearest neighbor search problem in large databases of 3D poses, where the matching is performed based on some low [38, 39] or high [40,41] level features extracted from the image.”
3D human pose from silhouettes by relevance vector regression (2004, methodology): “In particular, example based methods explicitly tore a set of training examples whose 3D poses are known, and estimate pose by searching for training image(s) similar to the given input image, and interpolating from their poses [2, 14, 9, 11].”
Disentangling Latent Hands for Image Synthesis and Pose Estimation (2018, background): “Early methods could recognize only a restricted set of poses [1, 36] or used simplified hand representations instead of full 3D skeletons [26, 37].”
Motion Capture of Hands in Action Using Discriminative Salient Points (2012, background): “Discriminative approaches instead do not require an explicit hand model, but learn a mapping from image features to hand poses from a large set of training data [20–23].”
Real-Time Articulated Hand Pose Estimation Using Semi-supervised Transductive Regression Forests (2013, methodology): “Hand pose estimation Earlier approaches for articulated hand pose estimation are diversified, such as coloured markers [6], probabilistic line matching [1], multi-camera network [13] and Bayesian filter with Chamfer matching [25].”
Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data (2013, methodology): “Discriminative Methods: A method for 3D hand pose estimation framed as a database indexing problem was proposed by Athitsos and Sclaroff [1].”
Real time hand pose estimation using depth sensors (2011, background): “[2] estimate 3D hand pose from a cluttered image.”
Sign Language Recognition (2011, methodology): “Athitsos and Sclaroff used a method for matching binary edges from cluttered images, to edges produced by model hand shapes [6].”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, methodology): “Athitsos and Sclaroff (2003) resort to probabilistic line matching, while Thayananthan et al (2003) combine Bayesian filtering with Chamfer matching.”
3D Hand Shape and Pose From Images in the Wild (2019, background): “When it comes to a monocular color input, the problem becomes inherently ill posed due to the increased depth and scale ambiguities, but that did not prevent several researchers [4, 9, 51, 57, 63, 39] from attempting to solve it in the past albeit with limited results.”