Reality Check:
How Avatar and Face Representation Affect the Perceptual Evaluation of Synthesized Gestures

ACM SIGGRAPH 2026

Haoyang Du1, Yinghan Xu2, John Dingliana2, Brian Keegan1, Rachel McDonnell2, Cathy Ennis3
1Technological University Dublin, 2Trinity College Dublin, 3Maynooth University
Paper Video
Seven avatar representations evaluated in this study

Fig. 1. The seven avatar representations evaluated in this study. From left to right: Gaussian Avatar (Reconstruction-based Avatars), Deploy-Hi and Deploy-Lo (high-fidelity and lightweight deployable assets), TexSMPL-X and UntexSMPL-X and Mann (standard research baselines), and Stick (minimalist kinematic visualization baseline). We explore how avatar and face visualization shapes perceptual evaluations of co-speech gestures in a series of 3 experiments.

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.

BibTeX

BibTeX not available yet — awaiting official ACM SIGGRAPH 2026 publication.