1,922 Hits in 5.3 sec

Multi-Exposure Image Fusion through Structural Patch Decomposition with Gaussian Filter

Avinash Sharma, Pallavi Parashar
2018 International Journal of Advanced Research in Computer Science and Software Engineering  
ghosting artifacts for dynamic scenes.  ...  It propose a simple yet effective Structural Patch Decomposition with Gaussian Filter (SPDGF) approach for multi-exposure image fusion (MEF) that is robust to ghosting effect.  ...  However, until now few works have been conducted on the performance evaluation of multi-exposure image fusion, especially colourful multi-exposure image fusion.  ... 
doi:10.23956/ijarcsse.v8i3.595 fatcat:fcqpffgyqvew7mlphwty6evohq

Merging-ISP: Multi-Exposure High Dynamic Range Image Signal Processing [article]

Prashant Chaudhari, Franziska Schirrmacher, Andreas Maier, Christian Riess, Thomas Köhler
2021 arXiv   pre-print
Merging-ISP enables direct reconstructions of HDR images of dynamic scenes from multiple raw CFA images with different exposures.  ...  High dynamic range (HDR) imaging combines multiple images with different exposure times into a single high-quality image.  ...  Conclusion We proposed an effective deep neural network architecture named Merging-ISP for multi-exposure HDR imaging of dynamic scenes.  ... 
arXiv:1911.04762v2 fatcat:6uptlalqrzfojhw4nznwychdcu

Perceptual Optimization of a Biologically-Inspired Tone Mapping Operator [article]

Peibei Cao, Chenyang Le, Yuming Fang, Kede Ma
2022 arXiv   pre-print
We then train another lightweight DNN to fuse the LDR image stack into a desired LDR image by maximizing a variant of MEF-SSIM, another perceptually calibrated metric for image fusion.  ...  With the increasing popularity and accessibility of high dynamic range (HDR) photography, tone mapping operators (TMOs) for dynamic range compression and medium presentation are practically demanding.  ...  ACKNOWLEDGMENT The authors would like to dedicate this humble piece of work to Prof. Ted Adelson for his 70th birthday 5 .  ... 
arXiv:2206.09146v1 fatcat:tg2frtsb5fdrpc4owot7apxnd4

Perceptual Quality Assessment for Multi-Exposure Image Fusion

Kede Ma, Kai Zeng, Zhou Wang
2015 IEEE Transactions on Image Processing  
of multi-exposure fused images.  ...  Multi-exposure image fusion (MEF) is considered an effective quality enhancement technique widely adopted in consumer electronics, but little work has been dedicated to the perceptual quality assessment  ...  Liu for providing the codes of [29] , Dr. B. Gu and Dr. Z. Li for generating fused images of their algorithms.  ... 
doi:10.1109/tip.2015.2442920 pmid:26068317 fatcat:fj3bcrdahnakpgg2gzey2cbpyi

Adaptive exposure fusion for high dynamic range imaging

Sidhdharthkumar Patel, Dimitrios Androutsos, Matthew Kyan
2015 2015 IEEE International Conference on Image Processing (ICIP)  
This paper proposes a novel exposure fusion algorithm that directly fuses exposure bracketed shots into a displayable image.  ...  The proposed method yields a perceptually detailed image when compared against other methods of similar nature.  ...  Reducing the dynamic range for displaying the image is termed tone mapping and its goal is to retain perceptually relevant information while discarding the rest.  ... 
doi:10.1109/icip.2015.7351694 dblp:conf/icip/PatelAK15 fatcat:we45ymeys5f5pfwqp67bm3qzqm

Exposure Fusion Algorithm Based on Perceptual Contrast and Dynamic Adjustment of Well-Exposedness [chapter]

Pablo Martínez-Cañada, Marius Pedersen
2014 Lecture Notes in Computer Science  
Results based on objective evaluation show that the proposed algorithm clearly outperforms the original exposure fusion technique and most of the state-of-the-art tone mapping operators for static images  ...  The luminance of natural scenes frequently presents a high dynamic range and cannot be adequately captured with traditional imaging devices.  ...  Their algorithm computes an image quality metric for each pixel in the multi-exposure sequence, which encodes perceptually desirable qualities, i.e. contrast, saturation and well-exposedness.  ... 
doi:10.1007/978-3-319-07998-1_21 fatcat:rqeh7e366nfwnkhzjmalj6ra3m

Deep Learning for HDR Imaging: State-of-the-Art and Future Trends [article]

Lin Wang, Kuk-Jin Yoon
2021 arXiv   pre-print
High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision.  ...  Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.  ...  ACKNOWLEDGMENTS This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2018R1A2B3008640).  ... 
arXiv:2110.10394v3 fatcat:pvsktnd5wrgo5lstughzlhon7i

Perceptual evaluation of multi-exposure image fusion algorithms

Kai Zeng, Kede Ma, Rania Hassen, Zhou Wang
2014 2014 Sixth International Workshop on Quality of Multimedia Experience (QoMEX)  
We then carry out a subjective user study using a multi-stimulus scoring approach to evaluate and compare the quality of the fused images.  ...  Multi-exposure image fusion is considered an effective and efficient quality enhancement technique widely adopted in consumer electronics products.  ...  Toet and Franken [24] examined the perceptual quality of multi-scale image fusion schemes, where only night-time outdoor scenes and very simple fusion methods were included in the study.  ... 
doi:10.1109/qomex.2014.6982278 dblp:conf/qomex/ZengMHW14 fatcat:mjo46lc425cori3gnib2cnq5w4

Multi-width Activation and Multiple Receptive Field Networks for Dynamic Scene Deblurring

Jinkai Cui, Weihong Li, Wei Guo, Weiguo Gong
2019 Asian Conference on Machine Learning  
In this paper, we propose an end-to-end multi-width activation and multiple receptive field networks for the large-scale and complicated dynamic scene deblurring.  ...  And then, we design the multi-scale feature fusion module, where a learning fusion structure is designed to adaptively fuse the multi-scale features and complicated blur information from the different  ...  Introduction Dynamic scene blur caused by the camera shake, object motions, different scene depths and occlusion in motion boundaries during the exposure time, and it is one of the most common image degradation  ... 
dblp:conf/acml/CuiLGG19 fatcat:2cpfkwjd7vfobminkvzl5cryoi

UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data [article]

Ru Li, Chuan Wang, Shuaicheng Liu, Jue Wang, Guanghui Liu, Bing Zeng
2021 arXiv   pre-print
The paper proposes a method to effectively fuse multi-exposure inputs and generates high-quality high dynamic range (HDR) images with unpaired datasets.  ...  The proposed method preserves the details of important regions and improves the total image perceptual quality.  ...  However, due to the lack of an explicit detection for the dynamic objects, the aforementioned methods are unaware of any motion in the scene, so as to be suitable for static scenes only. b) Dynamic scene  ... 
arXiv:2102.01850v1 fatcat:4mtioh22ezguxklshoq3z5eanq

Multi-Exposure Image Fusion Techniques: A Comprehensive Review

Fang Xu, Jinghong Liu, Yueming Song, Hui Sun, Xuan Wang
2022 Remote Sensing  
Then, based on the multi-exposure image sequences in static and dynamic scenes, we present a comparative study for 18 representative MEF approaches using nine commonly used objective fusion metrics.  ...  Multi-exposure image fusion (MEF) is emerging as a research hotspot in the fields of image processing and computer vision, which can integrate images with multiple exposure levels into a full exposure  ...  Acknowledgments: The authors wish to thank the associate editor and reviewers for their valuable suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs14030771 fatcat:bqzxhuh4drclbgbbbva4oso7g4

Multi-exposure image fusion: A patch-wise approach

Kede Ma, Zhou Wang
2015 2015 IEEE International Conference on Image Processing (ICIP)  
We propose a patch-wise approach for multi-exposure image fusion (MEF).  ...  Extensive experiments demonstrate the superiority of the proposed algorithm both qualitatively and quantitatively.  ...  Multi-exposure image fusion (MEF) alleviates the problem by taking multiple images of the same scene under different exposure levels and synthesizing a low dynamic range (LDR) image from them.  ... 
doi:10.1109/icip.2015.7351094 dblp:conf/icip/MaW15 fatcat:mlniyclywvd6vlof53oria5544

An Image Quality Assessment of Multi-Exposure Image Fusion by Improving SSIM

Sushmitha CM, Meharunnisa SP
2018 International Journal of Trend in Scientific Research and Development  
Multi-exposure image fusion (MEF) is viewed as a viable quality upgrade system generally received in purchaser hardware, A solitary caught picture of a genuine scene is normally lacking to uncover every  ...  In this paper a multi picture fusion(MEF) calculation by streamlining a target quality measure in particular the MEF auxiliary similitude list (MEF-SSIM).  ...  Multi exposure image fusion (MEF) is a cost effective technique that bridges the gap between the high dynamic range (HDR) of luminance levels in natural scenes and the low dynamic range (LDR) of standard  ... 
doi:10.31142/ijtsrd15634 fatcat:3cbdjpkc7vcizdamhkerbg2jre

HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset [article]

Guanying Chen, Chaofeng Chen, Shi Guo, Zhetong Liang, Kwan-Yee K. Wong, Lei Zhang
2021 arXiv   pre-print
sequences of static scenes and 184 testing pairs of dynamic scenes.  ...  Considering the fact that there is no publicly available dataset for quantitative and comprehensive evaluation of HDR video reconstruction methods, we collect such a benchmark dataset, which contains 97  ...  The ground-truth HDR frames for static scenes were generated by merging multi-exposure images [9] .  ... 
arXiv:2103.14943v2 fatcat:gwmm6rdpu5bdzeob3krfaijefq

Scene Segmentation-Based Luminance Adjustment for Multi-Exposure Image Fusion

Yuma Kinoshita, Hitoshi Kiya
2019 IEEE Transactions on Image Processing  
Multi-exposure image fusion is a method for producing images that are expected to be more informative and perceptually appealing than any of the input ones, by directly fusing photos taken with different  ...  We propose a novel method for adjusting luminance for multi-exposure image fusion. For the adjustment, two novel scene segmentation approaches based on luminance distribution are also proposed.  ...  and input multi-exposure images clearly cover the dynamic range of a scene.  ... 
doi:10.1109/tip.2019.2906501 fatcat:lq7lwuz4enckzjxagbabslg4ai
« Previous Showing results 1 — 15 out of 1,922 results