Oriel — AI & technology worth noticing, every day.

Task-Utility IQA: Rethinking Image Quality Assessment in Embodied Tasks

Paper · https://arxiv.org/abs/2610.35905

arXiv:2610.35905v1 Announce Type: new Abstract: Image quality assessment (IQA) underpins embodied imaging pipelines by judging whether visual quality satisfies downstream tasks, yet most existing methods learn task-agnostic scores aligned with generic human ratings on static benchmarks. This objective mismatches embodied and interactive settings, where image adequacy depends on task goals, context, and action requirements that shape an agent's decisions. We argue that IQA should shift from score regression to goal-conditioned judgment defined by embodied task utility. To this end, we propose an MLLM-based embodied IQA agent framework that reasons about task requirements, grounds quality evidence, and produces decision-facing assessments. A compact VisDrone evidence study shows that conventional perceptual metrics and generic MLLM-based IQA scores are weak proxies for downstream VLM task success, while a task-conditioned utility score better predicts whether visual input supports the target task. These findings support a task-utility-oriented reframing of IQA for embodied, explainable, and decision-aware visual perception.

First seen by Oriel on .

AI summary

This paper proposes reframing image quality assessment for embodied systems around task-conditioned utility rather than generic human-aligned quality scores.

  • The authors introduce an MLLM-based embodied IQA agent that reasons about task requirements, grounds visual evidence, and produces decision-facing assessments.
  • A compact VisDrone study finds conventional perceptual metrics and generic MLLM-based IQA scores weakly predict downstream VLM task success.
  • Task-conditioned utility scores better predict whether visual inputs support the target task.
  • The framework targets embodied, interactive, explainable, and decision-aware visual perception.

#image quality assessment #embodied ai #multimodal llms #computer vision

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2610.35905v1https://arxiv.org/abs/2610.35905 Read discussion