Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Zeng, Haijin"'
Coded Aperture Snapshot Spectral Imaging (CASSI) is a crucial technique for capturing three-dimensional multispectral images (MSIs) through the complex inverse task of reconstructing these images from coded two-dimensional measurements. Current state
Externí odkaz:
http://arxiv.org/abs/2409.07417
Snapshot Compressive Imaging (SCI) relies on decoding algorithms such as CNN or Transformer to reconstruct the hyperspectral image (HSI) from its compressed measurement. Although existing CNN and Transformer-based methods have proven effective, CNNs
Externí odkaz:
http://arxiv.org/abs/2408.00629
Transformer-based low-light enhancement methods have yielded promising performance by effectively capturing long-range dependencies in a global context. However, their elevated computational demand limits the scalability of multiple iterations in dee
Externí odkaz:
http://arxiv.org/abs/2406.01028
Autor:
Wu, Yaqi, Fan, Zhihao, Chu, Xiaofeng, Ren, Jimmy S., Li, Xiaoming, Yue, Zongsheng, Li, Chongyi, Zhou, Shangcheng, Feng, Ruicheng, Dai, Yuekun, Yang, Peiqing, Loy, Chen Change, Xu, Senyan, Sun, Zhijing, Zhu, Jiaying, Zhu, Yurui, Fu, Xueyang, Zha, Zheng-Jun, Cao, Jun, Li, Cheng, Chen, Shu, Ma, Liang, Zhou, Shiyang, Zeng, Haijin, Feng, Kai, Chen, Yongyong, Su, Jingyong, Guan, Xianyu, Yu, Hongyuan, Wan, Cheng, Lin, Jiamin, Han, Binnan, Zou, Yajun, Wu, Zhuoyuan, Huang, Yuan, Yu, Yongsheng, Zhang, Daoan, Li, Jizhe, Yin, Xuanwu, Zuo, Kunlong, Lu, Yunfan, Xu, Yijie, Ma, Wenzong, Guo, Weiyu, Xiong, Hui, Yu, Wei, Luo, Bingchun, Nathan, Sabari, Kansal, Priya
The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data fo
Externí odkaz:
http://arxiv.org/abs/2405.04867
This paper endeavors to advance the precision of snapshot compressive imaging (SCI) reconstruction for multispectral image (MSI). To achieve this, we integrate the advantageous attributes of established SCI techniques and an image generative model, p
Externí odkaz:
http://arxiv.org/abs/2311.11417
This paper presents a deep learning-based spectral demosaicing technique trained in an unsupervised manner. Many existing deep learning-based techniques relying on supervised learning with synthetic images, often underperform on real-world images esp
Externí odkaz:
http://arxiv.org/abs/2307.01990
Autor:
Zeng, Haijin, Cao, Jiezhang, Feng, Kai, Huang, Shaoguang, Zhang, Hongyan, Luong, Hiep, Philips, Wilfried
Hyperspectral imaging (HI) has emerged as a powerful tool in diverse fields such as medical diagnosis, industrial inspection, and agriculture, owing to its ability to detect subtle differences in physical properties through high spectral resolution.
Externí odkaz:
http://arxiv.org/abs/2305.04047
Autor:
Zeng, Haijin, Feng, Kai, Huang, Shaoguang, Cao, Jiezhang, Chen, Yongyong, Zhang, Hongyan, Luong, Hiep, Philips, Wilfried
Hyperspectral imaging systems that use multispectral filter arrays (MSFA) capture only one spectral component in each pixel. Hyperspectral demosaicing is used to recover the non-measured components. While deep learning methods have shown promise in t
Externí odkaz:
http://arxiv.org/abs/2303.13404
Autor:
Zeng, Haijin, Feng, Kai, Cao, Jiezhang, Huang, Shaoguang, Zhao, Yongqiang, Luong, Hiep, Aelterman, Jan, Philips, Wilfried
Pixel binning based Quad sensors have emerged as a promising solution to overcome the hardware limitations of compact cameras in low-light imaging. However, binning results in lower spatial resolution and non-Bayer CFA artifacts. To address these cha
Externí odkaz:
http://arxiv.org/abs/2303.13571
Spatial-Spectral Total Variation (SSTV) can quantify local smoothness of image structures, so it is widely used in hyperspectral image (HSI) processing tasks. Essentially, SSTV assumes a sparse structure of gradient maps calculated along the spatial
Externí odkaz:
http://arxiv.org/abs/2204.12879