Compositional Human Pose Regression

By Xiao Sun, Jiaxiang Shang, Shuang Liang, Yichen Wei. 2017

590 citations recorded by the source corpus.

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M [20] and is competitive with state-of-the-art results on MPII [3].

Subfields: Archeology, Computer Vision and Pattern Recognition, 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 Archeology

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

In Human-Computer Interaction

Citations in the corpus

Objects as Points (2019, neutral): “[49].”
Feature Boosting Network For 3D Pose Estimation (2019, methodology): “1 mm of the method in [30].”
2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, methodology): “Our approach for human pose estimation is a regression method, similarly to [28, 47, 9].”
End-to-End Recovery of Human Shape and Pose (2017, background): “[40] that regresses bones and obtains excellent results on the 3D pose benchmarks.”
Deep Learning-based Human Pose Estimation: A Survey (2020, methodology): “There are many works based on the regression framework (e.g., References [17, 54, 116, 118, 147, 148, 153, 154, 172, 178, 190, 222, 233, 284]) to predict joint coordinates from images as shown in Figure 2(a).”
Learning Monocular 3D Human Pose Estimation from Multi-view Images (2018, methodology): “Algorithms for 3D human pose estimation from single images [18, 27, 20, 15, 17, 23, 19, 31, 26, 25] have now matured to the point where they can operate in real-time and in the wild.”
Exploiting Temporal Information for 3D Human Pose Estimation (2017, background): “[15] designed a unified network that can regress both 2D and 3D poses at the same time given an image.”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, background): “The research can be categorized into sparse 2D parsing (2D skeleton estimation) [6, 39], sparse 3D parsing (3D skeleton estimation) [33, 44, 64, 48, 50, 35, 61], dense 2D parsing [17] and dense 3D parsing (shape and pose estimation).”
3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training (2018, methodology): “Protocol 2 reports the error after alignment with the ground truth in translation, rotation, and scale (P-MPJPE) [34, 50, 10, 40, 58, 16].”
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry (2019, methodology): “Single-view methods In many recent works, convolutional neural networks (CNN) are used to estimate the co-ordinates of the 3D joints directly from images [38, 39, 40, 35, 23].”
Integral Human Pose Regression (2017, methodology): “[38] find it helpful to reformulate the pose representation as bones instead of joints and then enhance the loss function.”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, methodology): “Finally, some recent approaches treat 2D and 3D pose estimation jointly or iteratively [45], [46], [47], [48], [49].”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, unknown): “Moreover, regression based methods are conceptually more adapted to 2D and 3D scenarios and can be used in-distinctly on both cases [36, 38].”
Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks (2019, methodology): “We perform 2D pose detections using the cascaded pyramid network (CPN) [6] which is an extension of FPN, as proposed in [39].”
Human Pose Regression with Residual Log-likelihood Estimation (2021, methodology): “Existing methods can be divided into two categories: heatmap-based [57, 56, 62, 4, 64, 54, 46, 52] and regression-based [58, 5, 53, 70, 42, 61].”
Monocular Total Capture: Posing Face, Body, and Hands in the Wild (2018, methodology): “Direct estimation methods predict 3D human pose directly from images, in the form of direct coordinate regression [46, 55, 56], voxel [42, 32, 66] or depth map [73].”
Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose (2020, background): “[57] proposed to use compositional loss, which exploits the joint connection structure.”
Video Based Reconstruction of 3D People Models (2018, background): “Recent works leverage 2D annotations to train networks for the task of 3D pose estimation [42, 53, 84, 65, 68, 56].”
Semantic Graph Convolutional Networks for 3D Human Pose Regression (2019, methodology): “Each bone is a directed vector pointing from the starting joint to its associated parent as defined in [53].”
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].”