2021 IEEE International Conference on Image Processing (ICIP) 2021
DOI: 10.1109/icip42928.2021.9506192
|View full text |Cite
|
Sign up to set email alerts
|

Convolutional Neural Networks for Omnidirectional Image Quality Assessment: Pre-Trained or Re-Trained?

Abstract: The use of convolutional neural networks (CNN) for image quality assessment (IQA) becomes many researcher's focus. Various pretrained models are fine-tuned and used for this task. In this paper, we conduct a benchmark study of seven state-of-the-art pre-trained models for IQA of omnidirectional images. To this end, we first train these models using an omnidirectional database and compare their performance with the pre-trained versions. Then, we compare the use of viewports versus equirectangular (ERP) images a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(2 citation statements)
references
References 18 publications
0
2
0
Order By: Relevance
“…We chose the ResNet-50 with its pre-trained weights obtained on the ImageNet [12] database as it is the most common and widely used. Furthermore, this choice is also motivated based on conclusions of a previous comparative study [27] for which it ranked the best compared to VGG-16/19, ResNet-18/34, and Inception-V3 models.…”
Section: Architecture Of the Modelmentioning
confidence: 99%
“…We chose the ResNet-50 with its pre-trained weights obtained on the ImageNet [12] database as it is the most common and widely used. Furthermore, this choice is also motivated based on conclusions of a previous comparative study [27] for which it ranked the best compared to VGG-16/19, ResNet-18/34, and Inception-V3 models.…”
Section: Architecture Of the Modelmentioning
confidence: 99%
“…In the extraction of these patches, the use of radial content (i.e. from the sphere) is highly recommended compared to the projected one [11,12]. This way, the geometric distortion induced by the sphere-to-plane projection can be avoided.…”
Section: Introductionmentioning
confidence: 99%