Posebits for Monocular Human Pose Estimation

By Gerard Pons-Moll, David J. Fleet, Bodo Rosenhahn. 2014

85 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “[204] Posebits Conc Lowlv Hand Herda et al.”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, background): “[63] proposed posebits which are semantic pose descriptors which represent geometrical relationships between body parts and can take binary values depending on the answer to simple questions such as “Left foot in front of the torso”.”
Ordinal Depth Supervision for 3D Human Pose Estimation (2018, background): “[35] where attributes regarding the relative 3D position of the body parts are included in their posebits database.”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, background): “Pons-Moll et al. [37] take a diﬀerent approach: they estimate qualitative “posebits” from mocap and relate these to 3D pose.”
Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision (2016, methodology): “Besides neural networks, regression forests have been used to derive 3D posebit descriptors, answering questions such as ”is the left leg in-front of the right leg”, to query 3D pose with corresponding annotation [53].”
VNect (2017, background): “2016] and classification over example poses [Pons-Moll et al. 2014; Rogez and Schmid 2016].”
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision (2016, methodology): “While CNNs dominate, regression forests have also been used to derive 3D posebit descriptors efficiently [43].”
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation (2018, result): “Pavlakos et al. [36] take another approach by relying on weak 3D supervision in form of a relative 3D ordering of joints, similar to the previously proposed PoseBits [40].”
Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera (2018, background): “Several works lift 2D detections to 3D using learning or geometric reasoning [18, 29, 35, 9, 26, 49, 33, 48, 44, 34, 13, 43, 45].”
Single-Shot Multi-person 3D Pose Estimation from Monocular RGB (2017, background): “Instead of a direct regression to pose, the bounding boxes are classiﬁed into a set of K-poses similar to [45].”
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing (2017, background): “There is a vast literature on monocular 3d human pose estimation, including the analysis of kinematic ambiguities associated with the 3d pose [42, 5], as well as generative and discriminative methods for learning and inference [35, 37, 4, 1, 26, 38, 14, 30].”
Bayesian Image Based 3D Pose Estimation (2016, methodology): “[25] use boolean relationships between body components, called posebits, for training an SVM for retrieving the 3D body pose.”
Video Based Reconstruction of 3D People Models (2018, background): “The reason is that pose differences induce additional 3D ambiguities which cannot be uniquely decoupled from global size, even on multiple frames [67, 61, 49].”
On Self-Contact and Human Pose (2021, background): “textual and ordinal descriptions of body pose [35, 36].”