Yulong Li, Yeyao Chen, Yueli Cui, Mei Yu. LF-UMTI: unsupervised multi-exposure light field image fusion based on multi-scale spatial-angular interaction[J]. Opto-Electronic Engineering, 2024, 51(6): 240093-1
- Opto-Electronic Engineering
- Vol. 51, Issue 6, 240093-1 (2024)
Fig. 1. Overall network diagram of the proposed method
Fig. 2. Light field spatial angular feature extraction module
Fig. 3. Light field information interaction module
Fig. 4. (a) Feature fusion module; (b) Bottleneck residual module
Fig. 5. Light field reconstruction module
Fig. 6. Some scene examples in the benchmark dataset established in this work
Fig. 7. Subjective comparison results of different methods on the established benchmark dataset
Fig. 8. Subjective comparison of depth maps estimated from the fused light field images obtained with different fusion methods
Fig. 9. Subjective comparison results of the main network structure ablation experiments
Fig. 10. Subjective comparison results of angle consistency loss ablation experiments
|
Table 1. Comparison of objective indicators among different methods on 50 testing scenarios
|
Table 2. Comparative results of objective indicators of the main network structure ablation experiments in this article
|
Table 3. Comparison results of running time and parameter quantities of different methods
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20