DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model

Abstract

The goal of this paper is to advance the state-of-the-art of articulated pose estimation in scenes with multiple people. To that end we contribute on three fronts. We propose (1) improved body part detectors that generate effective bottom-up proposals for body parts; (2) novel image-conditioned pairwise terms that allow to assemble the proposals into a variable number of consistent body part configurations; and (3) an incremental optimization strategy that explores the search space more efficiently thus leading both to better performance and significant speed-up factors. Evaluation is done on two single-person and two multi-person pose estimation benchmarks. The proposed approach significantly outperforms best known multi-person pose estimation results while demonstrating competitive performance on the task of single person pose estimation. Models and code available at http://pose.mpi-inf.mpg.de

ECCV'16. High-res version at https://www.d2.mpi-inf.mpg.de/sites/default/files/insafutdinov16arxiv.pdf

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Convolutional Pose Machines

Cited by in corpus (40)

• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Human pose estimation via Convolutional Part Heatmap Regression
• Human Pose Regression by Combining Indirect Part Detection and Contextual Information
• Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
• RMPE: Regional Multi-person Pose Estimation
• Towards human-level performance on automatic pose estimation of infant spontaneous movements
• Multi-Person Pose Estimation with Local Joint-to-Person Associations
• ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
• Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
• ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
• Integral Human Pose Regression
• SuPer Deep: A Surgical Perception Framework for Robotic Tissue Manipulation using Deep Learning for Feature Extraction
• Joint Multi-Person Pose Estimation and Semantic Part Segmentation
• Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation
• RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation
• Real-time Human Pose Estimation from Video with Convolutional Neural Networks
• EgoCap: Egocentric Marker-less Motion Capture with Two Fisheye Cameras
• 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras
• Combining detection and tracking for human pose estimation in videos
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• AMIL: Adversarial Multi Instance Learning for Human Pose Estimation
• Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
• EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
• Toward safe separation distance monitoring from RGB-D sensors in human-robot interaction
• A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms
• Collaborative Attention Network for Person Re-identification
• Exploiting skeletal structure in computer vision annotation with Benders decomposition
• Multi-Person Pose Estimation via Column Generation
• Bi-directional Graph Structure Information Model for Multi-Person Pose Estimation
• Improving Temporal Interpolation of Head and Body Pose using Gaussian Process Regression in a Matrix Completion Setting
• Efficient Pose and Cell Segmentation using Column Generation
• PedX: Benchmark Dataset for Metric 3D Pose Estimation of Pedestrians in Complex Urban Intersections
• Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
• Flow-Partitionable Signed Graphs
• Inter-Homines: Distance-Based Risk Estimation for Human Safety
• Simple Multi-Resolution Representation Learning for Human Pose Estimation
• Bottom-up Pose Estimation of Multiple Person with Bounding Box Constraint
• Motion Style Extraction Based on Sparse Coding Decomposition
• A Global to Local Double Embedding Method for Multi-person Pose Estimation
• An Empirical Study towards Understanding How Deep Convolutional Nets Recognize Falls