Compact Representation of Light Field Data for Refocusing and Focal Stack Reconstruction Using Depth Adaptive Multi-CNN

Zhao, Chun; Jeon, Byeungwoo

doi:10.1109/tci.2023.3347910

Cited by 3 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ensure the diversity of the application range of the proposed scheme, the DMAPs in this paper are extracted from the LF dataset instead of being directly downloaded from the Lytro camera. We adopt the method of Zhao, C. et al [42,43], and use the FS to simultaneously render the AIF image and DMAP. The AIF image refers to the set of all the best in-focus pixels in the FS, i.e., the best in-focus pixel at every position is gathered.…”

Section: Fs Transforms Into Aifmentioning

confidence: 99%

Content-Adaptive Light Field Contrast Enhancement Using Focal Stack and Hierarchical Network

Guo,

Yuan

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Light field (LF) cameras can capture a scene’s information from all different directions and provide comprehensive image information. However, the resulting data processing commonly encounters problems of low contrast and low image quality. In this article, we put forward a content-adaptive light field contrast enhancement scheme using a focal stack (FS) and hierarchical structure. The proposed FS set contained 300 light field images, which were captured using a Lytro-Illum camera. In addition, we integrated the classical Stanford Lytro Light Field Archive and JPEG Pleno Database. Specifically, according to the global brightness, the acquired LF images were classified into four different categories. First, we transformed the original LF FS into a depth map (DMAP) and all-in-focus (AIF) image. The image category was preliminarily determined depending on the brightness information. Then, the adaptive parameters were acquired by the corresponding multilayer perceptron (MLP) network training, which intrinsically enhanced the contrast and adjusted the light field image. Finally, our method automatically produced an enhanced FS based on the DMAP and AIF image. The experimental comparison results demonstrate that the adaptive values predicted by our MLP had high precision and approached the ground truth. Moreover, compared to existing contrast enhancement methods, our method provides a global contrast enhancement, which improves, without over-enhancing, local areas. The complexity of image processing is reduced, and real-time, adaptive LF enhancement is realized.

show abstract

Section: Fs Transforms Into Aifmentioning

confidence: 99%