Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Helge Rhodin

Helge Rhodin

AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Xingzhe He , Bastian Wandt , Helge Rhodin

Figure 1 for AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Figure 2 for AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Figure 3 for AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Figure 4 for AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints

Access Paper or Ask Questions

LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract

Xingzhe He , Bastian Wandt , Helge Rhodin

Figure 1 for LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract

Figure 2 for LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract

Figure 3 for LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract

Figure 4 for LatentKeypointGAN: Controlling Images via Latent Keypoints -- Extended Abstract

* CVPR Workshop 2022

Access Paper or Ask Questions

DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Shih-Yang Su , Timur Bagautdinov , Helge Rhodin

Figure 1 for DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Figure 2 for DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Figure 3 for DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

Figure 4 for DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks

* Project website: https://lemonatsu.github.io/danbo

Access Paper or Ask Questions

A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Eric Hedlin , Helge Rhodin , Kwang Moo Yi

Figure 1 for A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Figure 2 for A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Figure 3 for A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Figure 4 for A Simple Method to Boost Human Pose Estimation Accuracy by Correcting the Joint Regressor for the Human3.6m Dataset

Access Paper or Ask Questions

Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

Paritosh Parmar , Amol Gharat , Helge Rhodin

Figure 1 for Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

Figure 2 for Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

Figure 3 for Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

Figure 4 for Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment

Access Paper or Ask Questions

Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model

Michael Zwölfer , Dieter Heinrich , Kurt Schindelwig , Bastian Wandt , Helge Rhodin , Joerg Spoerri , Werner Nachbauer

Figure 1 for Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model

Figure 2 for Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model

Figure 3 for Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model

Figure 4 for Improved 2D Keypoint Detection in Out-of-Balance and Fall Situations -- combining input rotations and a kinematic model

* extended abstract, 4 pages, 3 figures, 2 tables

Access Paper or Ask Questions

AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

Mohsen Gholami , Bastian Wandt , Helge Rhodin , Rabab Ward , Z. Jane Wang

Figure 1 for AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

Figure 2 for AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

Figure 3 for AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

Figure 4 for AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation

Access Paper or Ask Questions

ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Bastian Wandt , James J. Little , Helge Rhodin

Figure 1 for ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Figure 2 for ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Figure 3 for ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Figure 4 for ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Access Paper or Ask Questions

GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation

Xingzhe He , Bastian Wandt , Helge Rhodin

Figure 1 for GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation

Figure 2 for GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation

Figure 3 for GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation

Figure 4 for GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation

Access Paper or Ask Questions