by   Boris N. Oreshkin, et al.

HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images. HybrIK has three major components: (1) pretrained convolution backbone, (2) deconvolution to lift 3D pose from 2D convolution features, (3) analytical inverse kinematics pass correcting deep learning prediction using learned distribution of plausible twist and swing angles. In this paper we propose an enhancement of the 2D to 3D lifting module, replacing deconvolution with Transformer, resulting in accuracy and computational efficiency improvement relative to the original HybrIK method. We demonstrate our results on commonly used H36M, PW3D, COCO and HP3D datasets. Our code is publicly available https://github.com/boreshkinai/hybrik-transformer.


page 1

page 2


AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation

Movement and pose assessment of newborns lets experienced pediatricians ...

GraFormer: Graph Convolution Transformer for 3D Pose Estimation

Exploiting relations among 2D joints plays a crucial role yet remains se...

Video based Object 6D Pose Estimation using Transformers

We introduce a Transformer based 6D Object Pose Estimation framework Vid...

Active Learning for Bayesian 3D Hand Pose Estimation

We propose a Bayesian approximation to a deep learning architecture for ...

ConvMAE: Masked Convolution Meets Masked Autoencoders

Vision Transformers (ViT) become widely-adopted architectures for variou...

Fast Nonconvex Deconvolution of Calcium Imaging Data

Calcium imaging data promises to transform the field of neuroscience by ...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset