# Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation

arXiv: https://arxiv.org/abs/2508.04049 · HTML: https://mlsanity.com/paper/2508.04049/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 6 Aug 2025.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [Two-Stream Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2211.01367/) (2022)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Gloss-free Sign Language Translation: Improving from Visual-Language Pretraining](https://mlsanity.com/paper/2307.14768/) (2023)
- [Arbitrary-steps Image Super-resolution via Diffusion Inversion](https://mlsanity.com/paper/2412.09013/) (2024)
- [LLMs are Good Sign Language Translators](https://mlsanity.com/paper/2404.00925/) (2024)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model](https://mlsanity.com/paper/2208.09141/) (2022)
- [RealisDance: Equip controllable character animation with realistic hands](https://mlsanity.com/paper/2409.06202/) (2024)
- [BEST: BERT Pre-Training for Sign Language Recognition with Coupling Tokenization](https://mlsanity.com/paper/2302.05075/) (2023)
- [T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text](https://mlsanity.com/paper/2406.07119/) (2024)
- [Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model](https://mlsanity.com/paper/2503.18512/) (2025)
- [A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars](https://mlsanity.com/paper/2401.04730/) (2024)
- [Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation](https://mlsanity.com/paper/2411.16810/) (2024)
- [Linguistics-Vision Monotonic Consistent Network for Sign Language Production](https://mlsanity.com/paper/2412.16944/) (2024)
- [SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation](https://mlsanity.com/paper/2506.11621/) (2025)

## Built on by (most cited first, 1 of 1)

- [A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production](https://mlsanity.com/paper/2602.11861/) (2026)

## Abstract (arXiv)

Sign language video generation requires producing natural signing motions with realistic appearances under precise semantic control, yet faces two critical challenges: excessive signer-specific data requirements and poor generalization. We propose a new paradigm for sign language video generation that decouples motion semantics from signer identity through a two-phase synthesis framework. First, we construct a signer-independent multimodal motion lexicon, where each gloss is stored as identity-agnostic pose, gesture, and 3D mesh sequences, requiring only one recording per sign. This compact representation enables our second key innovation: a discrete-to-continuous motion synthesis stage that transforms retrieved gloss sequences into temporally coherent motion trajectories, followed by identity-aware neural rendering to produce photorealistic videos of arbitrary signers. Unlike prior work constrained by signer-specific datasets, our method treats motion as a first-class citizen: the learned latent pose dynamics serve as a portable "choreography layer" that can be visually realized through different human appearances. Extensive experiments demonstrate that disentangling motion from identity is not just viable but advantageous - enabling both high-quality synthesis and unprecedented flexibility in signer personalization.