Exposure Interpolation Via Hybrid Learning

Zheng, Chaobing; Li, Zhengguo; Yang, Yi; Wu, Shiqian

doi:10.1109/icassp40776.2020.9053741

Cited by 10 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The VETHDR-Nikon dataset is from [61], [62], collected by a Nikon 7200 camera. It consists of original images in 8bit color JPEG files format.…”

Section: Resultsmentioning

confidence: 99%

“…The SVC can be easily inserted into other networks to process Bayer image with or without SVE, and can be redesigned into flexible variants when the data pattern or SVE changes. The exposure-guidance method can be used to study other HDRI problems, such as [61], [62], allowing CNN to reduce the interference of illexposed pixels. It is worth noting that the proposed algorithm can be further improved through the related technologies of augmentation and transfer learning.…”

Section: Conclusion Remarks and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot

Xu,

Liu,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Spatially varying exposure (SVE) is a promising choice for high-dynamic-range (HDR) imaging (HDRI). The SVEbased HDRI, which is called single-shot HDRI, is an efficient solution to avoid ghosting artifacts. However, it is very challenging to restore a full-resolution HDR image from a real-world image with SVE because: a) only one-third of pixels with varying exposures are captured by camera in a Bayer pattern, b) some of the captured pixels are over-and under-exposed. For the former challenge, a spatially varying convolution (SVC) is designed to process the Bayer images carried with varying exposures. For the latter one, an exposure-guidance method is proposed against the interference from over-and under-exposed pixels. Finally, a joint demosaicing and HDRI deep learning framework is formalized to include the two novel components and to realize an end-toend single-shot HDRI. Experiments indicate that the proposed end-to-end framework avoids the problem of cumulative errors and surpasses the related state-of-the-art methods.

show abstract

“…The VETHDR-Nikon dataset is from [61], [62], collected by a Nikon 7200 camera. It consists of original images in 8bit color JPEG files format.…”

Section: Resultsmentioning

confidence: 99%

Section: Conclusion Remarks and Discussionmentioning

confidence: 99%

Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot

Xu,

Liu,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Readers are invited to view to electronic version of figures and zoom in them so as to better appreciate differences among all images. The VETHDR-Nikon dataset is from [30], collected by a Nikon 7200 camera. It consists of 495 pairs of images in 8bit JPEG files format.…”

Section: Experiments Resultsmentioning

confidence: 99%

Intensity Mapping Functions For HDR Panorama Imaging: Weighted Histogram Averaging

Xu¹,

Li²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

It is challenging to stitch multiple images with different exposures due to possible color distortion and loss of details in the brightest and darkest regions of input images. In this paper, a novel color mapping algorithm is first proposed by introducing a new concept of weighted histogram averaging (WHA). The proposed WHA algorithm leverages the correspondence between the histogram bins of two images which are built up by using the non-decreasing property of the color mapping functions (CMFs). The WHA algorithm is then adopted to synthesize a set of differently exposed panorama images. The intermediate panorama images are finally fused via a state-of-the-art multi-scale exposure fusion (MEF) algorithm to produce the final panorama image. Extensive experiments indicate that the proposed WHA algorithm significantly surpasses the related state-of-the-art color mapping methods. The proposed high dynamic range (HDR) stitching algorithm based on MEF also preserves details in the brightest and darkest regions of the input images well. The related materials will be publicly accessible at https://github.com/yilun-xu/WHA for reproducible research.

show abstract

“…It captures long-range dependencies directly by computing interactions between any two positions regardless of their positional distance. This is important for those image processing problems which heavily depend on the longrange dependencies, such as single image de-noising [13], single image de-raining [15,16], high dynamic range imaging [17,18,19], and so on.…”

Section: Relevant Workmentioning

confidence: 99%

Non-Local Single Image DE-Raining Without Decomposition

Zheng

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

It is challenging to remove rain steaks from a single rainy image because the rain steaks are spatially varying in the rainy image. On top of a new insight in single image de-raining, a nonlocal de-raining algorithm is proposed in this paper to remove the rain streaks from the rainy image. The rainy image is not decomposed into different layers by the proposed algorithm. Experimental results validate the proposed algorithm.

show abstract

Exposure Interpolation Via Hybrid Learning

Cited by 10 publications

References 22 publications

Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot

Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot

Intensity Mapping Functions For HDR Panorama Imaging: Weighted Histogram Averaging

Non-Local Single Image DE-Raining Without Decomposition

Contact Info

Product

Resources

About