TY - GEN
T1 - Joint HDR Denoising and Fusion
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
AU - Liu, Shuaizheng
AU - Zhang, Xindong
AU - Sun, Lingchen
AU - Liang, Zhetong
AU - Zeng, Hui
AU - Zhang, Lei
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023/8
Y1 - 2023/8
N2 - Mobile phones have become a ubiquitous and indispensable photographing device in our daily life, while the small aperture and sensor size make mobile phones more susceptible to noise and over-saturation, resulting in low dynamic range (LDR) and low image quality. It is thus crucial to develop high dynamic range (HDR) imaging techniques for mobile phones. Unfortunately, the existing HDR image datasets are mostly constructed by DSLR cameras in daytime, limiting their applicability to the study of HDR imaging for mobile phones. In this work, we develop, for the first time to our best knowledge, an HDR image dataset by using mobile phone cameras, namely Mobile-HDR dataset. Specifically, we utilize three mobile phone cameras to collect paired LDR-HDR images in the raw image domain, covering both daytime and night-time scenes with different noise levels. We then propose a transformer based model with a pyramid cross-attention alignment module to aggregate highly correlated features from different exposure frames to perform joint HDR denoising and fusion. Experiments validate the advantages of our dataset and our method on mobile HDR imaging.
AB - Mobile phones have become a ubiquitous and indispensable photographing device in our daily life, while the small aperture and sensor size make mobile phones more susceptible to noise and over-saturation, resulting in low dynamic range (LDR) and low image quality. It is thus crucial to develop high dynamic range (HDR) imaging techniques for mobile phones. Unfortunately, the existing HDR image datasets are mostly constructed by DSLR cameras in daytime, limiting their applicability to the study of HDR imaging for mobile phones. In this work, we develop, for the first time to our best knowledge, an HDR image dataset by using mobile phone cameras, namely Mobile-HDR dataset. Specifically, we utilize three mobile phone cameras to collect paired LDR-HDR images in the raw image domain, covering both daytime and night-time scenes with different noise levels. We then propose a transformer based model with a pyramid cross-attention alignment module to aggregate highly correlated features from different exposure frames to perform joint HDR denoising and fusion. Experiments validate the advantages of our dataset and our method on mobile HDR imaging.
KW - Computational imaging
UR - https://www.scopus.com/pages/publications/85218205748
U2 - 10.1109/CVPR52729.2023.01342
DO - 10.1109/CVPR52729.2023.01342
M3 - Conference article published in proceeding or book
AN - SCOPUS:85218205748
SN - 9798350301298
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 13966
EP - 13975
BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023
PB - IEEE Computer Society
Y2 - 18 June 2023 through 22 June 2023
ER -