Avatar visual quality can mislead intent recognition accuracy
When Visual Quality Misleads: Intent Recognition under Rendered Avatar Distortions
MultimediaComputer Vision and Pattern RecognitionHuman-Computer Interaction
Summary
People often judge the quality of 3D avatars by how good they look, assuming this means the avatar clearly communicates actions or intentions. The authors tested this by showing participants avatars under different distortions and found many cases where an avatar looked good but people misread its actions. This means good visual quality doesn't always mean effective communication. The authors suggest new ways to measure avatar quality that include how well intentions are understood, not just how they look.
What this means in practice
- •For virtual reality developers: Improve avatar streaming by incorporating intent recognition metrics beyond visual fidelity for clearer user communication.
- •For video game studios: Design avatars and streaming systems that better preserve player intent under network or rendering distortions.
Authors
Ning-Hsuan Chang, Kai-Siang Ma, Yu-Chih Chen
Abstract
Avatar-streaming systems are commonly evaluated with image and video quality assessment (IQA/VQA) metrics, implicitly treating visual fidelity as a proxy for communicative success. We test this assumption through a controlled behavioral study of rendered 3D avatars across a pristine condition and fourteen geometric, photometric, temporal, and combined distortions. Fifty-nine participants contributed 2,688 judgments of perceived action, response confidence, and visual quality. We identify Misleading Quality in this dataset as distorted renderings that retain above-average perceived quality but yield below-average action-recognition accuracy. We also derive an Intent Quality Score (IQS) combining recognition correctness and confidence as the behavioral target for objective metrics. Among 126 distorted content--condition cells, 31 (24.6%) exhibited Misleading Quality; temporal and geometric distortions showed the highest rates, at 50.0% and 31.1%, respectively. The results reveal a quality--accuracy dissociation where distortion families affect appearance and communication differently. Across 24 direct-scoring IQA/VQA metrics and three supervised feature-regression baselines, alignment with IQS remained limited; at $λ=0.5$, the best leave-one-content-out baseline reached PLCC $=0.4435$. Under this controlled protocol, visual fidelity alone is insufficient for avatar communication, motivating intent-aware quality assessment and streaming objectives.