# Pose-Based Sign Language Appearance Transfer

arXiv: https://arxiv.org/abs/2410.13675 · HTML: https://mlsanity.com/paper/2410.13675/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Builds on (most cited first, 7 of 7)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [AUTSL: A Large Scale Multi-modal Turkish Sign Language Dataset and Baseline Methods](https://mlsanity.com/paper/2008.00932/) (2020)
- [Towards Privacy-Aware Sign Language Translation at Scale](https://mlsanity.com/paper/2402.09611/) (2024)
- [Evaluating the Immediate Applicability of Pose Estimation for Sign Language Recognition](https://mlsanity.com/paper/2104.10166/) (2021)
- [AnonySIGN: Novel Human Appearance Synthesis for Sign Language Video Anonymisation](https://mlsanity.com/paper/2107.10685/) (2021)
- [An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation](https://mlsanity.com/paper/2305.17714/) (2023)
- [pose-format: Library for Viewing, Augmenting, and Handling .pose Files](https://mlsanity.com/paper/2310.09066/) (2023)

## Built on by (most cited first, 2 of 2)

- [Stable Signer: Hierarchical Sign Language Generative Model](https://mlsanity.com/paper/2512.04048/) (2025)
- [Evaluation of Pose Estimation Systems for Sign Language Translation](https://mlsanity.com/paper/2604.24609/) (2026)

## Abstract (arXiv)

We introduce a method for transferring the signer's appearance in sign language skeletal poses while preserving the sign content. Using estimated poses, we transfer the appearance of one signer to another, maintaining natural movements and transitions. This approach improves pose-based rendering and sign stitching while obfuscating identity. Our experiments show that while the method reduces signer identification accuracy, it slightly harms sign recognition performance, highlighting a tradeoff between privacy and utility. Our code is available at https://github.com/sign-language-processing/pose-anonymization.