Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline

Article Types

Countries / Regions

Search Results (1)

Search Parameters:
Keywords = half-instance initialization network (HINet)

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 4849 KiB  
Article
Occlusion Removal in Light-Field Images Using CSPDarknet53 and Bidirectional Feature Pyramid Network: A Multi-Scale Fusion-Based Approach
by Mostafa Farouk Senussi and Hyun-Soo Kang
Appl. Sci. 2024, 14(20), 9332; https://doi.org/10.3390/app14209332 - 13 Oct 2024
Cited by 4 | Viewed by 2209
Abstract
Occlusion removal in light-field images remains a significant challenge, particularly when dealing with large occlusions. An architecture based on end-to-end learning is proposed to address this challenge that interactively combines CSPDarknet53 and the bidirectional feature pyramid network for efficient light-field occlusion removal. CSPDarknet53 [...] Read more.
Occlusion removal in light-field images remains a significant challenge, particularly when dealing with large occlusions. An architecture based on end-to-end learning is proposed to address this challenge that interactively combines CSPDarknet53 and the bidirectional feature pyramid network for efficient light-field occlusion removal. CSPDarknet53 acts as the backbone, providing robust and rich feature extraction across multiple scales, while the bidirectional feature pyramid network enhances comprehensive feature integration through an advanced multi-scale fusion mechanism. To preserve efficiency without sacrificing the quality of the extracted feature, our model uses separable convolutional blocks. A simple refinement module based on half-instance initialization blocks is integrated to explore the local details and global structures. The network’s multi-perspective approach guarantees almost total occlusion removal, enabling it to handle occlusions of varying sizes or complexity. Numerous experiments were run on sparse and dense datasets with varying degrees of occlusion severity in order to assess the performance. Significant advancements over the current cutting-edge techniques are shown in the findings for the sparse dataset, while competitive results are obtained for the dense dataset. Full article
(This article belongs to the Special Issue Advanced Pattern Recognition & Computer Vision)
Show Figures

Figure 1

Back to TopTop