Recent advancements in the field of No-Reference Image Quality Assessment (NR-IQA) using deep learning techniques demonstrate high performance across multiple open-source datasets. However, such models are typically very large and complex making them not so suitable for real-world deployment, especially on resource- and battery-constrained mobile devices. To address this limitation, we propose a compact, lightweight NR-IQA model that achieves state-of-the-art (SOTA) performance on ECCV AIM UHD-IQA challenge validation and test datasets while being also nearly 5.7 times faster than the fastest SOTA model. Our model features a dual-branch architecture, with each branch separately trained on synthetically and authentically distorted images which enhances the model's generalizability across different distortion types. To improve robustness under diverse real-world visual conditions, we additionally incorporate multiple color spaces during the training process. We also demonstrate the higher accuracy of recently proposed Kolmogorov-Arnold Networks (KANs) for final quality regression as compared to the conventional Multi-Layer Perceptrons (MLPs). Our evaluation considering various open-source datasets highlights the practical, high-accuracy, and robust performance of our proposed lightweight model. Code: https://github.com/nasimjamshidi/LAR-IQA.

翻译：近年来，利用深度学习技术的无参考图像质量评估领域取得了显著进展，在多个开源数据集上展现出卓越性能。然而，此类模型通常规模庞大且结构复杂，使其不太适合在现实世界中部署，尤其是在资源和电池受限的移动设备上。为解决这一局限，我们提出了一种紧凑、轻量级的NR-IQA模型。该模型在ECCV AIM UHD-IQA挑战赛的验证和测试数据集上实现了最先进的性能，同时其推理速度比当前最快的SOTA模型快了近5.7倍。我们的模型采用双分支架构，每个分支分别在合成失真和真实失真图像上进行训练，从而增强了模型对不同失真类型的泛化能力。为了提升模型在多样真实视觉条件下的鲁棒性，我们在训练过程中额外引入了多种色彩空间。我们还证明了，与传统的多层感知机相比，近期提出的Kolmogorov-Arnold网络在最终质量回归任务中具有更高的准确性。我们在多个开源数据集上的评估结果表明，所提出的轻量级模型具有实用、高精度和鲁棒的性能。代码：https://github.com/nasimjamshidi/LAR-IQA。