3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network

By Sijin Li, Antoni B. Chan. 2014

485 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Feature Boosting Network For 3D Pose Estimation (2019, methodology): “For example, Li and Chan [17] designed a pretraining strategy, in which the 3D pose regressor was initialized with a model trained for body part detection.”
Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach (2017, methodology): “Deep neural networks [13, 33] trained on these datasets do not generalize well to other environments, such as in the wild.”
Single-Shot Multi-person 3D Pose Estimation from Monocular RGB (2017, background): “Single-Person 3D Pose Estimation : Existing monocular single-person 3D pose methods show good performance on standard datasets [18, 51, 59, 41, 28, 27].”
Learning Deconvolution Network for Semantic Segmentation (2015, background): “, semantic segmentation [19, 1], human pose estimation [18], and so on.”
Hand Pose Estimation via Latent 2.5D Heatmap Regression (2018, background): “These approaches aim to learn a direct mapping from RGB images to 3D pose [48–50].”
Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks (2019, unknown): “For the first category, Li and Chan [24] designed a multitask framework that jointly learns pose regression and body part detectors.”
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing (2017, methodology): “More recently, deep convolutional architectures have been employed in order to estimate 3d pose directly from images[21, 22, 34, 51] mostly in connection with 3d human motion capture datasets like HumanEva, Human3.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “Model-free (1) Single-stage : direct prediction (Li and Chan, 2014; Pavlakos et al., 2017), body structure constraint (Li et al., 2015b; Tekin et al., 2016; Sun et al., 2017; Pavlakos et al., 2018a) (2) 2D-to-3D : (Martinez et al., 2017; Zhou et al., 2017; Tekin et al., 2017; Li and Lee, 2019;…”
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision (2016, background): “[31] report that predicting positions relative to the parent joint of the skeleton improves performance, but we show that a pose-dependent combination of absolute and relative positions leads to further improvements.”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, methodology): “Recently, this has been naturally extended to end-to-end mappings using CNN architectures, either in monocular images [7], [8], [12], [41], [42], [43] or in videos [11], [44].”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, background): “Many recent works follow the end-to-end paradigm [48, 40, 42, 46, 55], using images as input to predict 3D joint locations [23, 45, 34, 28], regress 3D heatmaps [31], or classify the image in a particular pose class [39, 40].”
Learning Pose Grammar to Encode Human Body Configuration for 3D Pose Estimation (2017, background): “Speciﬁcally, for the ﬁrst framework, (Li and Chan 2014) proposed a multi-task convolutional network that simultaneously learns pose regression and part detection.”
Unite the People: Closing the Loop Between 3D and 2D Human Representations (2017, background): “More recently, these representations have taken new popularity in approaches that fit detailed surfaces of a body model to images [4, 14, 16, 25, 44].”
Learning Monocular 3D Human Pose Estimation from Multi-view Images (2018, methodology): “In the top portion of Table 1, we report the MPJPE and NMPJPE values of fully-supervised methods on H36M using the same protocol as in [13, 31, 16, 26, 18, 19]: Five subjects (S1, S5, S6, S7, S8) are used for training and the remaining two (S9, S11) for testing.”
LCR-Net: Localization-Classiﬁcation-Regression for Human Pose (unknown): “They can be divided into two groups: (a) methods which ﬁrst search the image for local body parts and model their dependencies using biologically inspired graphical models [6, 30]; and (b) holistic approaches that directly estimate the full body [4, 14, 15, 19, 31].”
Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense (2019, methodology): “Single-view 3D Human Pose Estimation: Previous methods on 3D pose estimation can be divided into two streams: (i) directly learning 3D pose from a 2D image [36, 23], and (ii) cascaded frameworks that first perform 2D pose”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “In the work of Li and Chan [69], deep convolutional networks (ConvNets) are trained for two distinct approaches: (i) they jointly train the pose regression task with a set of detection tasks in a heterogeneous multi-task learning framework and (ii) pre-train the network using the detection tasks, an”
StarMap for Category-Agnostic Keypoint and Viewpoint Estimation (2018, background): “Toshev et al. [35] ﬁrst trained a deep neural network for 2D human pose regression and Li et al. [14] extended this approach to 3D. Starting from Tompson et al. [34], the heatmap representation has dominated the 2D key-point estimation community and has achieved great success in both 2D human pose…”
3D Human Pose Estimation in the Wild by Adversarial Learning (2018, background): “The pioneer work [22] proposed a multi-task framework that jointly trains pose regression and body part detectors.”
Bayesian Image Based 3D Pose Estimation (2016, background): “In the last years many works have approached the estimation of the poses via deep learning as in [13–16].”