DiffSign: AI-Assisted Generation of Customizable Sign Language Videos With Enhanced Realism

TL;DR

DiffSign is a novel AI system that generates realistic, customizable sign language videos by combining parametric retargeting and diffusion-based generative models, enhancing accessibility for the Deaf community.

Contribution

It introduces a hybrid approach that retargets human poses to 3D avatars and uses diffusion models conditioned on multimodal prompts for realistic, customizable sign language video synthesis.

Findings

Generated videos show improved realism and temporal consistency.

Supports multimodal prompts for diverse signer customization.

Useful for signer anonymization and accessibility enhancement.

Abstract

The proliferation of several streaming services in recent years has now made it possible for a diverse audience across the world to view the same media content, such as movies or TV shows. While translation and dubbing services are being added to make content accessible to the local audience, the support for making content accessible to people with different abilities, such as the Deaf and Hard of Hearing (DHH) community, is still lagging. Our goal is to make media content more accessible to the DHH community by generating sign language videos with synthetic signers that are realistic and expressive. Using the same signer for a given media content that is viewed globally may have limited appeal. Hence, our approach combines parametric modeling and generative modeling to generate realistic-looking synthetic signers and customize their appearance based on user preferences. We first retarget human sign language poses to 3D sign language avatars by optimizing a parametric model. The high-fidelity poses from the rendered avatars are then used to condition the poses of synthetic signers generated using a diffusion-based generative model. The appearance of the synthetic signer is controlled by an image prompt supplied through a visual adapter. Our results show that the sign language videos generated using our approach have better temporal consistency and realism than signing videos generated by a diffusion model conditioned only on text prompts. We also support multimodal prompts to allow users to further customize the appearance of the signer to accommodate diversity (e.g. skin tone, gender). Our approach is also useful for signer anonymization.