# RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360degImage Quality Assessment

arXiv: https://arxiv.org/abs/2603.14297 · HTML: https://mlsanity.com/paper/2603.14297/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 83 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 30 of 41)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)
- [Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward](https://mlsanity.com/paper/1801.00054/) (2017)
- [RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content](https://mlsanity.com/paper/2101.10955/) (2021)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)
- [ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration](https://mlsanity.com/paper/2411.19548/) (2024)
- [GIQA: Generated Image Quality Assessment](https://mlsanity.com/paper/2003.08932/) (2020)
- [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://mlsanity.com/paper/2303.12384/) (2023)
- [Perceptual Quality Assessment of Omnidirectional Images](https://mlsanity.com/paper/2207.02674/) (2022)
- [Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks](https://mlsanity.com/paper/2002.09140/) (2020)
- [PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas](https://mlsanity.com/paper/2306.01531/) (2023)
- [No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness](https://mlsanity.com/paper/2102.11393/) (2021)
- [NTIRE 2024 Quality Assessment of AI-Generated Content Challenge](https://mlsanity.com/paper/2404.16687/) (2024)
- [Bridge the Gap Between VQA and Human Behavior on Omnidirectional Video: A Large-Scale Dataset and a Deep Learning Model](https://mlsanity.com/paper/1807.10990/) (2018)
- [Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment](https://mlsanity.com/paper/2305.10983/) (2023)
- [One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework](https://mlsanity.com/paper/2505.11131/) (2025)
- [Generative Regression Based Watch Time Prediction for Short-Video Recommendation](https://mlsanity.com/paper/2412.20211/) (2024)
- [Reflections on Shannon Information: In search of a natural information-entropy for images](https://mlsanity.com/paper/1609.01117/) (2016)

## Built on by (most cited first, 2 of 2)

- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [Mover360: Controllable Object Manipulation in 360deg Panoramic Images](https://mlsanity.com/paper/2608.23238/) (2026)

## Abstract (arXiv)

Blind 360degimage quality assessment (IQA) aims to predict perceptual quality for panoramic images without a pristine reference. Unlike conventional planar images, 360degcontent 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 360degIQA. 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.