针对全景图像局部失真评估难题，提出多任务辅助网络提升质量预测精度。
Multitask Auxiliary Network for Perceptual Quality Assessment of Non-Uniformly Distorted Omnidirectional Images
- 设计多任务辅助网络，动态分配特征以应对非均匀失真。
- 在两个大规模数据集上超越现有方法，全图与局部质量评估更准确。
- 适合需要精准评估视频压缩或传输中局部失真的研究者使用。
全景图像质量评估（OIQA）近年来取得显著进展，但多数研究聚焦于均匀失真场景，难以处理非均匀失真问题。为此，本文提出一种用于非均匀失真全景图像的多任务辅助网络，通过联合训练主任务与多个辅助任务优化参数。模型包含三部分：提取视口序列多尺度特征的主干网络、动态分配特征的多任务特征选择模块，以及引导模型捕捉局部失真和全局质量变化的辅助子网络。在两个大规模OIQA数据库上的大量实验表明，所提方法优于现有最优指标，辅助子网络有效提升了性能。代码已公开于https://github.com/RJL2000/MTAOIQA。
原文摘要 · Abstract (English)
Omnidirectional image quality assessment (OIQA) has been widely investigated in the past few years and achieved much success. However, most of existing studies are dedicated to solve the uniform distortion problem in OIQA, which has a natural gap with the non-uniform distortion problem, and their ability in capturing non-uniform distortion is far from satisfactory. To narrow this gap, in this paper, we propose a multitask auxiliary network for non-uniformly distorted omnidirectional images, where the parameters are optimized by jointly training the main task and other auxiliary tasks. The proposed network mainly consists of three parts: a backbone for extracting multiscale features from the viewport sequence, a multitask feature selection module for dynamically allocating specific features to different tasks, and auxiliary sub-networks for guiding the proposed model to capture local distortion and global quality change. Extensive experiments conducted on two large-scale OIQA databases demonstrate that the proposed model outperforms other state-of-the-art OIQA metrics, and these auxiliary sub-networks contribute to improve the performance of the proposed model. The source code is available at https://github.com/RJL2000/MTAOIQA.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。