RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360°Image Quality Assessment

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yujia, Li, Yuyan, Liu, Jiuming, Zhang, Fang-Lue, Zheng, Xinhu, Dodgson, Neil. A
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915864288165888
author Wang, Yujia
Li, Yuyan
Liu, Jiuming
Zhang, Fang-Lue
Zheng, Xinhu
Dodgson, Neil. A
author_facet Wang, Yujia
Li, Yuyan
Liu, Jiuming
Zhang, Fang-Lue
Zheng, Xinhu
Dodgson, Neil. A
contents Blind 360°image quality assessment (IQA) aims to predict perceptual quality for panoramic images without a pristine reference. Unlike conventional planar images, 360°content in immersive environments restricts viewers to a limited viewport at any moment, making viewing behaviors critical to quality perception. Although existing scanpath-based approaches have attempted to model viewing behaviors by approximating the human view-then-rate paradigm, they treat scanpath generation and quality assessment as separate steps, preventing end-to-end optimization and task-aligned exploration. To address this limitation, we propose RL-ScanIQA, a reinforcement-learned framework for blind 360°IQA. RL-ScanIQA optimize a PPO-trained scanpath policy and a quality assessor, where the policy receives quality-driven feedback to learn task-relevant viewing strategies. To improve training stability and prevent mode collapse, we design multi-level rewards, including scanpath diversity and equator-biased priors. We further boost cross-dataset robustness using distortion-space augmentation together with rank-consistent losses that preserve intra-image and inter-image quality orderings. Extensive experiments on three benchmarks show that RL-ScanIQA achieves superior in-dataset performance and cross-dataset generalization. Codes are available at https://github.com/wangyuji1/RLScanIQA.git.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14297
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360°Image Quality Assessment
Wang, Yujia
Li, Yuyan
Liu, Jiuming
Zhang, Fang-Lue
Zheng, Xinhu
Dodgson, Neil. A
Computer Vision and Pattern Recognition
Blind 360°image quality assessment (IQA) aims to predict perceptual quality for panoramic images without a pristine reference. Unlike conventional planar images, 360°content in immersive environments restricts viewers to a limited viewport at any moment, making viewing behaviors critical to quality perception. Although existing scanpath-based approaches have attempted to model viewing behaviors by approximating the human view-then-rate paradigm, they treat scanpath generation and quality assessment as separate steps, preventing end-to-end optimization and task-aligned exploration. To address this limitation, we propose RL-ScanIQA, a reinforcement-learned framework for blind 360°IQA. RL-ScanIQA optimize a PPO-trained scanpath policy and a quality assessor, where the policy receives quality-driven feedback to learn task-relevant viewing strategies. To improve training stability and prevent mode collapse, we design multi-level rewards, including scanpath diversity and equator-biased priors. We further boost cross-dataset robustness using distortion-space augmentation together with rank-consistent losses that preserve intra-image and inter-image quality orderings. Extensive experiments on three benchmarks show that RL-ScanIQA achieves superior in-dataset performance and cross-dataset generalization. Codes are available at https://github.com/wangyuji1/RLScanIQA.git.
title RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360°Image Quality Assessment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.14297