# Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production

arXiv: https://arxiv.org/abs/2412.13609 · HTML: https://mlsanity.com/paper/2412.13609/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 54 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Adversarial Training for Multi-Channel Sign Language Production](https://mlsanity.com/paper/2008.12405/) (2020)
- [Quantitative Survey of the State of the Art in Sign Language Recognition](https://mlsanity.com/paper/2008.09918/) (2020)
- [G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model](https://mlsanity.com/paper/2208.09141/) (2022)
- [Data Augmentation for Sign Language Gloss Translation](https://mlsanity.com/paper/2105.07476/) (2021)
- [SignDiff: Diffusion Model for American Sign Language Production](https://mlsanity.com/paper/2308.16082/) (2023)
- [Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Production](https://mlsanity.com/paper/2112.05277/) (2021)
- [Shaping a Stabilized Video by Mitigating Unintended Changes for Concept-Augmented Video Editing](https://mlsanity.com/paper/2410.12526/) (2024)

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

- [Linguistics-Vision Monotonic Consistent Network for Sign Language Production](https://mlsanity.com/paper/2412.16944/) (2024)
- [Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition](https://mlsanity.com/paper/2506.12848/) (2025)
- [SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation](https://mlsanity.com/paper/2506.11621/) (2025)
- [Context-Aware Autoregressive Diffusion for Gloss-Wise Sign Language Production](https://mlsanity.com/paper/2606.21234/) (2026)
- [BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production](https://mlsanity.com/paper/2606.28673/) (2026)
- [StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation](https://mlsanity.com/paper/2506.13156/) (2025)
- [Spoofing-aware Prompt Learning for Unified Physical-Digital Facial Attack Detection](https://mlsanity.com/paper/2512.06363/) (2025)
- [A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production](https://mlsanity.com/paper/2602.11861/) (2026)
- [Controllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades](https://mlsanity.com/paper/2603.08028/) (2026)
- [Towards Multi-View Sign Language Understanding: A Benchmark Dataset and Baseline](https://mlsanity.com/paper/2604.18184/) (2026)
- [The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production](https://mlsanity.com/paper/2606.22959/) (2026)
- [Physics-Informed Diffusion for Biomechanically Plausible 3D Sign Language Generation](https://mlsanity.com/paper/2607.14836/) (2026)
- [Bridging the Gap Between Semantics and Reconstruction:Unifying Sign Language Translation and Production](https://mlsanity.com/paper/2608.09045/) (2026)
- [SignRR: Retrieve and Refine Real Motion for Sign Language Production](https://mlsanity.com/paper/2608.28568/) (2026)
- [SignGPT: Toward LLM-Mediated Sign Language Interaction through Gloss-Free Translation and Generation](https://mlsanity.com/paper/2609.21709/) (2026)
- [Naturalness-guided Manifold Flow Matching for Sign Language Production](https://mlsanity.com/paper/2609.33339/) (2026)

## Abstract (arXiv)

Sign Language Production (SLP) aims to generate semantically consistent sign videos from textual statements, where the conversion from textual glosses to sign poses (G2P) is a crucial step. Existing G2P methods typically treat sign poses as discrete three-dimensional coordinates and directly fit them, which overlooks the relative positional relationships among joints. To this end, we provide a new perspective, constraining joint associations and gesture details by modeling the limb bones to improve the accuracy and naturalness of the generated poses. In this work, we propose a pioneering iconicity disentangled diffusion framework, termed Sign-IDD, specifically designed for SLP. Sign-IDD incorporates a novel Iconicity Disentanglement (ID) module to bridge the gap between relative positions among joints. The ID module disentangles the conventional 3D joint representation into a 4D bone representation, comprising the 3D spatial direction vector and 1D spatial distance vector between adjacent joints. Additionally, an Attribute Controllable Diffusion (ACD) module is introduced to further constrain joint associations, in which the attribute separation layer aims to separate the bone direction and length attributes, and the attribute control layer is designed to guide the pose generation by leveraging the above attributes. The ACD module utilizes the gloss embeddings as semantic conditions and finally generates sign poses from noise embeddings. Extensive experiments on PHOENIX14T and USTC-CSL datasets validate the effectiveness of our method. The code is available at: https://github.com/NaVi-start/Sign-IDD.