Filters








12,227 Hits in 9.7 sec

Pyramid Inter-Attention for High Dynamic Range Imaging

Sungil Choi, Jaehoon Cho, Wonil Song, Jihwan Choe, Jisung Yoo, Kwanghoon Sohn
2020 Sensors  
This paper proposes a novel approach to high-dynamic-range (HDR) imaging of dynamic scenes to eliminate ghosting artifacts in HDR images when in the presence of severe misalignment (large object or camera  ...  motion) in input low-dynamic-range (LDR) images.  ...  All LDR images were captured using a Samsung Galaxy S20 device. Conclusions We developed a novel end-to-end approach to reconstructing ghost-free HDR images of dynamic scenes.  ... 
doi:10.3390/s20185102 pmid:32906841 fatcat:irhq32swi5byrf4urguyjrcole

An Improved HDR Technique by Classification Method

Deepali Agarwal, Shilky Shrivastava, Anand Singh Bisen
2015 International Journal of Computer Applications  
Now a day, HDR image is mostly used in applications of wide range such as next generation broadcast, digital cinema and digital photography, because of its high quality and its good expression ability.  ...  These images can be further improved by further LDR technique. Finally, we combine all these images and obtain a final image. This final image will be better as compared to the original image.  ...  The goal of [45] is to deliver an up-to-date review of the suggested approaches for generation of ghost-free HDR image.  ... 
doi:10.5120/21174-4087 fatcat:icmx4jnldvazbfnfarsgbj3iue

HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensors [article]

Yitong Jiang, Inchang Choi, Jun Jiang, Jinwei Gu
2021 arXiv   pre-print
We propose a novel high dynamic range (HDR) video reconstruction method with new tri-exposure quad-bayer sensors.  ...  In order to better adapt the network to the large dynamic range, we also propose LDR-reconstruction loss that takes equal contributions from both the highlighted and the shaded pixels of HDR frames.  ...  All of these methods apply a simple global tone mapping with a fixed parameter [21, 22, 40, 42] on output and label HDR images to make the network adapt to a large dynamic range.  ... 
arXiv:2103.10982v1 fatcat:rdjzi2mgwffrdezns4uzcrakrm

Multi-Scale Dense Networks for Deep High Dynamic Range Imaging

Qingsen Yan, Dong Gong, Pingping Zhang, Qinfeng Shi, Jinqiu Sun, Ian Reid, Yanning Zhang
2019 2019 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Multi-scale dense networks for deep high dynamic range imaging  ...  Acknowledgment The work was partially supported by grants NSF of  ...  Our goal is to generate a ghost-free HDR image H, which is aligned with the reference image L 2 .  ... 
doi:10.1109/wacv.2019.00012 dblp:conf/wacv/YanGZSSRZ19 fatcat:fooutalrgfdbbkx45plwuhkql4

Omnidirectional ghost imaging system unwrapping-free panoramic ghost imaging [article]

Huan Cui, Jie Cao, Qun Hao, Dong Zhou, Mingyuan Tang, Kaiyu Zhang, Yingqiang Zhang
2021 arXiv   pre-print
Ghost imaging (GI) is a novel imaging method, which can reconstruct the object information by the light intensity correlation measurements.  ...  To enlarge FOV of GI efficiently, here we proposed the omnidirectional ghost imaging system (OGIS), which can achieve a 360 omnidirectional FOV at one shot only by adding a curved mirror.  ...  Introduction Unlike the traditional imaging via a pixelated detector array, ghost imaging (GI) is a novel imaging method using a bucket detector with no spatial resolution, which can reconstruct the object  ... 
arXiv:2108.05096v1 fatcat:36kshrq2xbhwlmly3afn5unp44

Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

Qingsen Yan, Dong Gong, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To avoid the ghosting from the source, we propose a novel attention-guided end-to-end deep neural network (AHDRNet) to produce high-quality ghost-free HDR images.  ...  Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.  ...  High dynamic range (HDR) imaging has been developed to compensate for these limitations, and ideally aims to generate a single image that represents a broad range of illuminations.  ... 
doi:10.1109/cvpr.2019.00185 dblp:conf/cvpr/YanGSHS0Z19 fatcat:7thlhytwbfaedmrhhattv7axvm

Attention-guided Network for Ghost-free High Dynamic Range Imaging [article]

Qingsen Yan, Dong Gong, Qinfeng Shi, Anton van den Hengel, Chunhua Shen, Ian Reid, Yanning Zhang
2019 arXiv   pre-print
To avoid the ghosting from the source, we propose a novel attention-guided end-to-end deep neural network (AHDRNet) to produce high-quality ghost-free HDR images.  ...  Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.  ...  High dynamic range (HDR) imaging has been developed to compensate for these limitations, and ideally aims to generate a single image that represents a broad range of illuminations.  ... 
arXiv:1904.10293v1 fatcat:6ory5drrdrcthabok27ezrylnq

SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes [article]

Wei Li, Shuai Xiao, Tianhong Dai, Shanxin Yuan, Tao Wang, Cheng Li, Fenglong Song
2022 arXiv   pre-print
Ghosting artifacts, motion blur, and low fidelity in highlight are the main challenges in High Dynamic Range (HDR) imaging from multiple Low Dynamic Range (LDR) images.  ...  These issues come from using the medium-exposed image as the reference frame in previous methods. To deal with them, we propose to use the under-exposed image as the reference to avoid these issues.  ...  As shown in Figure 4 (a), in the case of ultra-high dynamic range scene that occlusion occurs in saturated regions, our proposed method obtain a ghost-free results compared with other baselines that  ... 
arXiv:2206.09611v1 fatcat:sbxp3tm6lzg33l6z2a2u5z2jte

Navigated abdominal T1-W MRI permits free-breathing image acquisition with less motion artifact

Shreyas S. Vasanawala, Yuji Iwadate, Daniel G. Church, Robert J. Herfkens, Anja C. Brau
2010 Pediatric Radiology  
T1-weighted imaging in the pediatric abdomen suffers from respiratory motion artifacts.  ...  This work demonstrates the feasibility and potential utility of navigation for pediatric abdominal T1-weighted imaging.  ...  Acknowledgments The authors are grateful for support of the NIH (R01 EB009690).  ... 
doi:10.1007/s00247-009-1502-4 pmid:20066407 pmcid:PMC3004966 fatcat:7kc3bb56rrckjev6zgmz2xyjv4

Casual 6-DoF: free-viewpoint panorama using a handheld 360 camera [article]

Rongsen Chen, Fang-Lue Zhang, Simon Finnie, Andrew Chalmers, Teahyun Rhee
2022 arXiv   pre-print
Our method consists of 360 data capturing, novel depth estimation to produce a high-quality spherical depth panorama, and high-fidelity free-viewpoint generation.  ...  This paper presents a novel method to provide 6-DoF experiences over a wide area using an unstructured collection of 360 panoramas captured by a conventional 360 camera.  ...  In this paper, we present a novel method of performing wide-area free-viewpoint navigation using casually captured 360°p anoramas.  ... 
arXiv:2203.16756v1 fatcat:7zabtcsfa5a4vjp3su3g2sidfm

Ghost imaging based on Y-net: a dynamic coding and conjugate-decoding approach [article]

Ruiguo Zhu, Hong Yu, Zhijie Tan, Ronghua Lu, Shensheng Han, Zengfeng Huang, Jian Wang
2020 arXiv   pre-print
Here we propose a ghost imaging scheme based on a novel conjugate-decoding deep learning framework (Y-net), which works well under both deterministic and indeterministic illumination.  ...  Benefited from the end-to-end characteristic of our network, the image of a sample can be achieved directly from a pair of correlated speckles collected by the detectors, and the sample is illuminated  ...  Conclusion In summary, we have demonstrated a ghost imaging scheme based on Y-net, a novel conjugatedecoding deep learning framework that can be used to reconstruct sample images in both static and dynamic  ... 
arXiv:2002.03824v2 fatcat:qp5gpu2c75akzll6eo4pccs4ju

Wavelet-Based Network For High Dynamic Range Imaging [article]

Tianhong Dai, Wei Li, Xilei Cao, Jianzhuang Liu, Xu Jia, Ales Leonardis, Youliang Yan, Shanxin Yuan
2022 arXiv   pre-print
High dynamic range (HDR) imaging from multiple low dynamic range (LDR) images has been suffering from ghosting artifacts caused by scene and objects motion.  ...  In this work, we propose a novel frequency-guided end-to-end deep neural network (FHDRNet) to conduct HDR fusion in the frequency domain, and Discrete Wavelet Transform (DWT) is used to decompose inputs  ...  INTRODUCTION H IGH dynamic range (HDR) imaging using multiple low dynamic range (LDR) images as inputs is a technique used in computational photography to generate high-quality HDR images.  ... 
arXiv:2108.01434v2 fatcat:we43omyflvh4zcwqxh6udy6bsi

Interactive free-viewpoint video generation

Yanru Wang, Zhihao Huang, Hao Zhu, Wei Li, Xun Cao, Ruigang Yang
2020 Virtual Reality & Intelligent Hardware  
On the user interface, a dynamic video is presented, in which the user can select any viewpoint within the view range.  ...  Some problems remain to be solved in the future. For example, the images generated by the CNN typically feature blurred boundaries for wide-baseline pairs of input images.  ... 
doi:10.1016/j.vrih.2020.04.004 fatcat:dell5kveurhlhe7d5rp3unm3oi

Deep High Dynamic Range Imaging with Large Foreground Motions [chapter]

Shangzhe Wu, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang
2018 Lecture Notes in Computer Science  
This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions.  ...  In stark contrast to flow-based methods, we formulate HDR imaging as an image translation problem without optical flows.  ...  Introduction Off-the-shelf digital cameras typically fail to capture the entire dynamic range of a 3D scene.  ... 
doi:10.1007/978-3-030-01216-8_8 fatcat:kmwcpvrw2bcv5i6ulxxrcp7j6q

Fast multi-exposure image fusion with median filter and recursive filter

Shutao Li, Xudong Kang
2012 IEEE transactions on consumer electronics  
Another advantage is that a novel histogram equalization and median filter based motion detection method is proposed for fusing multi-exposure images in dynamic scenes which contain motion objects.  ...  The main advantage of the proposed method lies in a recursive filter based weight map refinement step which is able to obtain accurate weight maps for image fusion.  ...  ACKNOWLEDGMENT This paper is supported by the National Natural Science Foundation of China (No. 61172161).  ... 
doi:10.1109/tce.2012.6227469 fatcat:grw2bos34rbuzlh5ec4k53ifaq
« Previous Showing results 1 — 15 out of 12,227 results