3D Human Pose and Shape Estimation via HybrIK-Transformer
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 18 references that are in the map. First posted on arXiv 9 Feb 2023.
Builds on
16 of 18 references.
References · 16
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
- 2017End-to-end Recovery of Human Shape and Posecited by 885
- 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
- 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
- 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
- 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 307
- 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
- 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
- 2021Mesh Graphormercited by 265
4 more
- 2017Integral Human Pose Regressioncited by 256
- 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
- 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
- 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.