Pose Prediction

20 papers with code • 3 benchmarks • 2 datasets

Pose prediction is to predict future poses given a window of previous poses.

Greatest papers with code

Real-Time Seamless Single Shot 6D Object Pose Prediction

Microsoft/singleshotpose CVPR 2018

For single object and multiple object pose estimation on the LINEMOD and OCCLUSION datasets, our approach substantially outperforms other recent CNN-based approaches when they are all used without post-processing.

6D Pose Estimation using RGB Drone Pose Estimation +1

3D Hand Shape and Pose from Images in the Wild

yihui-he/epipolar-transformers CVPR 2019

We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild.

Pose Prediction

Protein-Ligand Scoring with Convolutional Neural Networks

gnina/gnina 8 Dec 2016

A CNN scoring function automatically learns the key features of protein-ligand interactions that correlate with binding.

Drug Discovery Pose Prediction

Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

xingyizhou/pose-hg-3d ICCV 2017

We propose a weakly-supervised transfer learning method that uses mixed 2D and 3D labels in a unified deep neutral network that presents two-stage cascaded structure.

Monocular 3D Human Pose Estimation Pose Prediction +1

Segmentation-driven 6D Object Pose Estimation

cvlab-epfl/segmentation-driven-pose CVPR 2019

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm.

6D Pose Estimation 6D Pose Estimation using RGB +1

Do Different Tracking Tasks Require Different Appearance Models?

Zhongdao/UniTrack 5 Jul 2021

We show how most tracking tasks can be solved within this framework, and that the same appearance model can be used to obtain performance that is competitive against specialised methods for all the five tasks considered.

Multi-Object Tracking Multi-Object Tracking and Segmentation +10

Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild

akashsengupta1997/STRAPS-3DHumanShapePose 21 Sep 2020

Thus, we propose STRAPS (Synthetic Training for Real Accurate Pose and Shape), a system that utilises proxy representations, such as silhouettes and 2D joints, as inputs to a shape and pose regression neural network, which is trained with synthetic training data (generated on-the-fly during training using the SMPL statistical body model) to overcome data scarcity.

Data Augmentation Keypoint Detection +1