Exposure-Aware Dynamic Weighted Learning for Single-Shot HDR Imaging

Vien, An Gia; Lee, Chul

doi:10.1007/978-3-031-20071-7_26

Cited by 3 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cheng and Chen [45] developed a learned kernel-based frame interpolation algorithm that learns deformable offsets for adaptive kernel shapes. Vien and Lee [44] developed a dynamic interpolation network that learns local filter coefficients to combine useful information and restore missing information. In this work, we develop an RGBW remosaicing algorithm based on learned kernel-based interpolation that learns the dynamic filter coefficients and adaptive kernel shapes to take into account an irregular grid of W pixels.…”

Section: Learned Kernel-based Interpolationmentioning

confidence: 99%

Learned Kernel-Based Interpolation for Efficient RGBW Remosaicing

Vien,

Lee

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

RGBW remosaicing is an interpolation technique that converts RGBW images captured using RGBW color filtering arrays into Bayer images. Although recent learning-based approaches using convolutional neural networks have shown substantial performance improvements, most algorithms require high computational and memory complexities, which limit their practical applicability. In this work, we propose an efficient and effective RGBW remosaicing algorithm based on learned kernel-based interpolation. First, the proposed algorithm extracts deep feature maps from input RGBW images. Then, we develop a learned kernel-based interpolation module composed of local and non-local interpolation blocks that generates two intermediate Bayer images. Specifically, the local interpolation block learns local filters to recover a Bayer image, whereas the non-local interpolation block recovers a Bayer image by estimating the non-local filters of dynamic shapes. Finally, a reconstructed Bayer image is obtained by combining the complementary information from the intermediate Bayer images using a spatially weighted fusion block. Experimental results demonstrate that the proposed algorithm achieves comparable or even better performance than stateof-the-art algorithms while providing the lowest computational and memory complexities.INDEX TERMS RGBW color filter array (CFA), Bayer CFA, remosaicing, learned kernel-based interpolation.

show abstract

Section: Learned Kernel-based Interpolationmentioning

confidence: 99%