# Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark

Source: [Express4D: Expressive, Friendly, and Extensible 4D Facial Motion Generation Benchmark](<https://www.sota2.com/research/paper/68fa7aa81e209131cea84734>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:24:53.663Z

Authors: Yaron Aloni, Rotem Shalev-Arkushin, Yonatan Shafir, Guy Tevet, Ohad Fried, Amit Haim Bermano

Published: 2025-08-17T17:10:13.000Z

## Abstract

Dynamic facial expression generation from natural language is a crucial task in Computer Graphics, with applications in Animation, Virtual Avatars, and Human-Computer Interaction. However, current generative models suffer from datasets that are either speech-driven or limited to coarse emotion labels, lacking the nuanced, expressive descriptions needed for fine-grained control, and were captured using elaborate and expensive equipment. We hence present a new dataset of facial motion sequences featuring nuanced performances and semantic annotation. The data is easily collected using commodity equipment and LLM-generated natural language instructions, in the popular ARKit blendshape format. This provides riggable motion, rich with expressive performances and labels. We accordingly train two baseline models, and evaluate their performance for future benchmarking. Using our Express4D dataset, the trained models can learn meaningful text-to-expression motion generation and capture the many-to-many mapping of the two modalities. The dataset, code, and video examples are available on our webpage: https://jaron1990.github.io/Express4D/

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Text-to-Motion Generation on KeyframeFace (test)](<https://www.sota2.com/research/sota/text-to-motion-generation-on-keyframeface-test.md>): Text-to-motion generation; KeyframeFace (test); FID: 0.0348.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.12438>)

[PDF](<https://arxiv.org/pdf/2508.12438.pdf>)