# When Visual Quality Misleads: Intent Recognition under Rendered Avatar Distortions

arXiv: https://arxiv.org/abs/2609.27560 · HTML: https://mlsanity.com/paper/2609.27560/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Builds on (most cited first, 4 of 4)

- [Image Quality Assessment using Contrastive Learning](https://mlsanity.com/paper/2110.13266/) (2021)
- [SJTU-TMQA: A quality assessment database for static mesh with texture map](https://mlsanity.com/paper/2309.15675/) (2023)
- [Understanding the Predictability of Gesture Parameters from Speech and their Perceptual Importance](https://mlsanity.com/paper/2010.00995/) (2020)
- [Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality](https://mlsanity.com/paper/2408.07041/) (2024)

## Abstract (arXiv)

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.