# Light Field Image Quality Assessment With Auxiliary Learning Based on Depthwise and Anglewise Separable Convolutions

arXiv: https://arxiv.org/abs/2412.07079 · HTML: https://mlsanity.com/paper/2412.07079/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 54 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 14 of 14)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Learning-Based View Synthesis for Light Field Cameras](https://mlsanity.com/paper/1609.02974/) (2016)
- [Resnet in Resnet: Generalizing Residual Architectures](https://mlsanity.com/paper/1603.08029/) (2016)
- [XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification](https://mlsanity.com/paper/1911.03803/) (2019)
- [Light Field Saliency Detection with Deep Convolutional Networks](https://mlsanity.com/paper/1906.08331/) (2019)
- [Tensor Oriented No-Reference Light Field Image Quality Assessment](https://mlsanity.com/paper/1909.02358/) (2019)
- [No-Reference Light Field Image Quality Assessment Based on Spatial-Angular Measurement](https://mlsanity.com/paper/1908.06280/) (2019)
- [Efficient No-Reference Quality Assessment and Classification Model for Contrast Distorted Images](https://mlsanity.com/paper/1804.02554/) (2018)
- [Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks](https://mlsanity.com/paper/1609.05672/) (2016)

## Built on by (most cited first, 3 of 3)

- [NeRF-NQA: No-Reference Quality Assessment for Scenes Generated by NeRF and Neural View Synthesis Methods](https://mlsanity.com/paper/2412.08029/) (2024)
- [NVS-SQA: Exploring Self-Supervised Quality Representation Learning for Neurally Synthesized Scenes without References](https://mlsanity.com/paper/2501.06488/) (2025)
- [DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment](https://mlsanity.com/paper/2507.19418/) (2025)

## Abstract (arXiv)

In multimedia broadcasting, no-reference image quality assessment (NR-IQA) is used to indicate the user-perceived quality of experience (QoE) and to support intelligent data transmission while optimizing user experience. This paper proposes an improved no-reference light field image quality assessment (NR-LFIQA) metric for future immersive media broadcasting services. First, we extend the concept of depthwise separable convolution (DSC) to the spatial domain of light field image (LFI) and introduce "light field depthwise separable convolution (LF-DSC)", which can extract the LFI's spatial features efficiently. Second, we further theoretically extend the LF-DSC to the angular space of LFI and introduce the novel concept of "light field anglewise separable convolution (LF-ASC)", which is capable of extracting both the spatial and angular features for comprehensive quality assessment with low complexity. Third, we define the spatial and angular feature estimations as auxiliary tasks in aiding the primary NR-LFIQA task by providing spatial and angular quality features as hints. To the best of our knowledge, this work is the first exploration of deep auxiliary learning with spatial-angular hints on NR-LFIQA. Experiments were conducted in mainstream LFI datasets such as Win5-LID and SMART with comparisons to the mainstream full reference IQA metrics as well as the state-of-the-art NR-LFIQA methods. The experimental results show that the proposed metric yields overall 42.86% and 45.95% smaller prediction errors than the second-best benchmarking metric in Win5-LID and SMART, respectively. In some challenging cases with particular distortion types, the proposed metric can reduce the errors significantly by more than 60%.