# Improving 3D Pose Estimation for Sign Language

arXiv: https://arxiv.org/abs/2308.09525 · HTML: https://mlsanity.com/paper/2308.09525/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [Panoptic Studio: A Massively Multiview System for Social Interaction Capture](https://mlsanity.com/paper/1612.03153/) (2016)
- [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues](https://mlsanity.com/paper/2007.12131/) (2020)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [An Analysis of SVD for Deep Rotation Estimation](https://mlsanity.com/paper/2006.14616/) (2020)
- [Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image](https://mlsanity.com/paper/1701.00295/) (2017)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [BBC-Oxford British Sign Language Dataset](https://mlsanity.com/paper/2111.03635/) (2021)
- [A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image](https://mlsanity.com/paper/1609.09058/) (2016)
- [Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency](https://mlsanity.com/paper/1909.06119/) (2019)
- [3D Pose Estimation and Future Motion Prediction from 2D Images](https://mlsanity.com/paper/2111.13285/) (2021)

## Built on by (most cited first, 16 of 16)

- [A Data-Driven Representation for Sign Language Production](https://mlsanity.com/paper/2404.11499/) (2024)
- [SignRep: Enhancing Self-Supervised Sign Representations](https://mlsanity.com/paper/2503.08529/) (2025)
- [Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation](https://mlsanity.com/paper/2506.00129/) (2025)
- [Hands-On: Segmenting Individual Signs from Continuous Sequences](https://mlsanity.com/paper/2504.08593/) (2025)
- [Sign Stitching: A Novel Approach to Sign Language Production](https://mlsanity.com/paper/2405.07663/) (2024)
- [Meaningful Pose-Based Sign Language Evaluation](https://mlsanity.com/paper/2510.07453/) (2025)
- [Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization](https://mlsanity.com/paper/2504.06610/) (2025)
- [SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work](https://mlsanity.com/paper/2508.06951/) (2025)
- [Modelling the Distribution of Human Motion for Sign Language Assessment](https://mlsanity.com/paper/2408.10073/) (2024)
- [Using Sign Language Production as Data Augmentation to enhance Sign Language Translation](https://mlsanity.com/paper/2506.09643/) (2025)
- [SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning](https://mlsanity.com/paper/2603.10446/) (2026)
- [Two Hands Are Better Than One: Resolving Hand to Hand Intersections via Occupancy Networks](https://mlsanity.com/paper/2404.05414/) (2024)
- [PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation](https://mlsanity.com/paper/2407.10220/) (2024)
- [SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation](https://mlsanity.com/paper/2507.09266/) (2025)
- [A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production](https://mlsanity.com/paper/2602.11861/) (2026)
- [SignRR: Retrieve and Refine Real Motion for Sign Language Production](https://mlsanity.com/paper/2608.28568/) (2026)

## Abstract (arXiv)

This work addresses 3D human pose reconstruction in single images. We present a method that combines Forward Kinematics (FK) with neural networks to ensure a fast and valid prediction of 3D pose. Pose is represented as a hierarchical tree/graph with nodes corresponding to human joints that model their physical limits. Given a 2D detection of keypoints in the image, we lift the skeleton to 3D using neural networks to predict both the joint rotations and bone lengths. These predictions are then combined with skeletal constraints using an FK layer implemented as a network layer in PyTorch. The result is a fast and accurate approach to the estimation of 3D skeletal pose. Through quantitative and qualitative evaluation, we demonstrate the method is significantly more accurate than MediaPipe in terms of both per joint positional error and visual appearance. Furthermore, we demonstrate generalization over different datasets. The implementation in PyTorch runs at between 100-200 milliseconds per image (including CNN detection) using CPU only.