Reality Check: How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures
Haoyang Du, Yinghan Xu, John Dingliana, Brian Keegan, Rachel McDonnell + 1 more
TLDR
This paper shows avatar and face rendering significantly bias perceptual judgments of synthesized gestures, offering guidelines for evaluation and deployment.
Key contributions
- Evaluated co-speech gestures using seven diverse avatar renderings.
- Demonstrated that avatar and face presentation systematically shift perceptual judgments.
- Provided recommendations for benchmarking gesture synthesis.
- Offered guidelines for deploying virtual humans in human-facing applications.
Why it matters
Perceptual evaluation is crucial for realistic virtual humans, but biases from avatar appearance can skew results. This work provides critical insights into these biases, ensuring more reliable evaluation and deployment of virtual humans. It helps researchers and developers create more accurate and effective virtual human experiences.
Original Abstract
The capacity to create realistic virtual humans has progressed significantly, and such characters can be found in many applications across entertainment, education and health. As an essential element of interactive virtual humans, speech-driven 3D gesture generation still depends heavily on perceptual evaluation, yet studies often vary avatar appearance and facial presentation when judging the generated motions. Prior work suggests these visual choices can bias motion judgments, but controlled evidence remains limited. We address this gap with controlled evaluations of co-speech gestures across motion sources, spanning seven representative avatar renderings used in contemporary research and application pipelines. Our results show that avatar and face presentation systematically shift perceptual judgments, and we provide recommendations for benchmarking gesture synthesis as well as for deploying virtual humans in human-facing applications.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.