TY - JOUR
T1 - Detail-Preserving Multi-Exposure Fusion with Edge-Preserving Structural Patch Decomposition
AU - Li, Hui
AU - Chan, Tsz Nam
AU - Qi, Xianbiao
AU - Xie, Wuyuan
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China under Grant 61902251.
Publisher Copyright:
© 1991-2012 IEEE.
PY - 2021/11
Y1 - 2021/11
N2 - The multi-exposure fusion (MEF) methods have received much attention in recent years due to the importance of constructing high dynamic range images. Among most of the existing studies, multi-scale structural-patch-decomposition-based MEF (MSPD-MEF) has achieved state-of-the-art fusion quality and the fastest running time. However, this method still suffers from detail loss in the fused images. To tackle this issue, we first incorporate the edge-preserving factors into this method to preserve the details in the fused images in a single-scale setting. Then, we develop the novel and flexible bell curve function, which can further preserve the details in both bright and dark regions. After that, we also show that our method can seamlessly plug in to this multi-scale framework. Extensive experimental results indicate that the proposed method can produce pleasing fusion results with little artifacts and low computational cost in both static and dynamic scenes.
AB - The multi-exposure fusion (MEF) methods have received much attention in recent years due to the importance of constructing high dynamic range images. Among most of the existing studies, multi-scale structural-patch-decomposition-based MEF (MSPD-MEF) has achieved state-of-the-art fusion quality and the fastest running time. However, this method still suffers from detail loss in the fused images. To tackle this issue, we first incorporate the edge-preserving factors into this method to preserve the details in the fused images in a single-scale setting. Then, we develop the novel and flexible bell curve function, which can further preserve the details in both bright and dark regions. After that, we also show that our method can seamlessly plug in to this multi-scale framework. Extensive experimental results indicate that the proposed method can produce pleasing fusion results with little artifacts and low computational cost in both static and dynamic scenes.
KW - Computational efficiency
KW - Dynamic range
KW - edge-preserving
KW - high dynamic range imaging
KW - Image edge detection
KW - Kernel
KW - Multi-exposure fusion
KW - Smoothing methods
KW - structural patch decomposition
KW - Task analysis
KW - Visualization
UR - http://www.scopus.com/inward/record.url?scp=85100487828&partnerID=8YFLogxK
U2 - 10.1109/TCSVT.2021.3053405
DO - 10.1109/TCSVT.2021.3053405
M3 - Journal article
AN - SCOPUS:85100487828
SN - 1051-8215
VL - 31
SP - 4293
EP - 4304
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
IS - 11
ER -