中文
相关论文

相关论文: Semantic-embedded Unsupervised Spectral Reconstruc…

200 篇论文

Self-similarity learning has been recognized as a promising method for single image super-resolution (SR) to produce high-resolution (HR) image in recent years. The performance of learning based SR reconstruction, however, highly depends on…

计算机视觉与模式识别 · 计算机科学 2018-09-28 Jiahe Shi , Chun Qi

While raw images exhibit advantages over sRGB images (e.g., linearity and fine-grained quantization level), they are not widely used by common users due to the large storage requirements. Very recent works propose to compress raw images by…

计算机视觉与模式识别 · 计算机科学 2023-03-01 Yufei Wang , Yi Yu , Wenhan Yang , Lanqing Guo , Lap-Pui Chau , Alex Kot , Bihan Wen

Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on…

计算机视觉与模式识别 · 计算机科学 2021-04-16 Junlin Han , Mehrdad Shoeiby , Tim Malthus , Elizabeth Botha , Janet Anstee , Saeed Anwar , Ran Wei , Lars Petersson , Mohammad Ali Armin

Hyperspectral image restoration faces several challenges, including limited training data, strong sensor specificity, and high spectral dimensionality. These limitations hinder the learning of robust hyperspectral priors, motivating the…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Daniele Picone , Mohamad Jouni , Mauro Dalla-Mura

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image…

计算机视觉与模式识别 · 计算机科学 2020-04-28 Zhi-Song Liu , Wan-Chi Siu , Li-Wen Wang , Chu-Tak Li , Marie-Paule Cani , Yui-Lam Chan

In medical image segmentation, supervised deep networks' success comes at the cost of requiring abundant labeled data. While asking domain experts to annotate only one or a few of the cohort's images is feasible, annotating all available…

计算机视觉与模式识别 · 计算机科学 2021-10-06 Devavrat Tomar , Behzad Bozorgtabar , Manana Lortkipanidze , Guillaume Vray , Mohammad Saeed Rad , Jean-Philippe Thiran

Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP). Computational photography tasks such as image denoising and colour constancy are commonly performed in the RAW domain, in part due…

图像与视频处理 · 电气工程与系统科学 2022-09-23 Marcos V. Conde , Steven McDonagh , Matteo Maggioni , Aleš Leonardis , Eduardo Pérez-Pellitero

Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands. However, this modeling strategy ignores the continuous nature of spectral signature. In this paper, we propose…

计算机视觉与模式识别 · 计算机科学 2022-09-01 Ruikang Xu , Mingde Yao , Chang Chen , Lizhi Wang , Zhiwei Xiong

We show how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image. The network takes an RGB image as input, regresses albedo and normal maps from which we compute lighting coefficients.…

计算机视觉与模式识别 · 计算机科学 2018-11-30 Ye Yu , William A. P. Smith

Deep learning-based methods for low-light image enhancement typically require enormous paired training data, which are impractical to capture in real-world scenarios. Recently, unsupervised approaches have been explored to eliminate the…

计算机视觉与模式识别 · 计算机科学 2021-12-06 Feng Zhang , Yuanjie Shao , Yishi Sun , Kai Zhu , Changxin Gao , Nong Sang

Deep learning methods have shown remarkable performance in image denoising, particularly when trained on large-scale paired datasets. However, acquiring such paired datasets for real-world scenarios poses a significant challenge. Although…

图像与视频处理 · 电气工程与系统科学 2023-08-15 Xin Lin , Chao Ren , Xiao Liu , Jie Huang , Yinjie Lei

Image denoising is often empowered by accurate prior information. In recent years, data-driven neural network priors have shown promising performance for RGB natural image denoising. Compared to classic handcrafted priors (e.g., sparsity…

图像与视频处理 · 电气工程与系统科学 2022-02-16 Yu-Chun Miao , Xi-Le Zhao , Xiao Fu , Jian-Li Wang , Yu-Bang Zheng

Most computer vision and machine learning-based approaches for historical document analysis are tailored to grayscale or RGB images and thus, mostly exploit their spatial information. Multispectral (MS) and hyperspectral (HS) images…

计算机视觉与模式识别 · 计算机科学 2023-03-10 M. Ljubenovic , P. Guzzonato , G. Franceschin , A. Traviglia

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

计算机视觉与模式识别 · 计算机科学 2024-05-14 Zuan Gao , Yuxin Wang , Yadong Qu , Boqiang Zhang , Zixiao Wang , Jianjun Xu , Hongtao Xie

Automatic Perceptual Image Quality Assessment is a challenging problem that impacts billions of internet, and social media users daily. To advance research in this field, we propose a Mixture of Experts approach to train two separate…

计算机视觉与模式识别 · 计算机科学 2023-05-30 Avinab Saha , Sandeep Mishra , Alan C. Bovik

Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…

计算机视觉与模式识别 · 计算机科学 2023-03-20 Yuhao Lin , Haiming Xu , Lingqiao Liu , Jinan Zou , Javen Qinfeng Shi

Ensuring data privacy and protection has become paramount in the era of deep learning. Unlearnable examples are proposed to mislead the deep learning models and prevent data from unauthorized exploration by adding small perturbations to…

密码学与安全 · 计算机科学 2024-06-26 Ruohan Meng , Chenyu Yi , Yi Yu , Siyuan Yang , Bingquan Shen , Alex C. Kot

Hyperspectral imaging acquires data in both the spatial and frequency domains to offer abundant physical or biological information. However, conventional hyperspectral imaging has intrinsic limitations of bulky instruments, slow data…

图像与视频处理 · 电气工程与系统科学 2023-04-06 Yuhyun Ji , Sang Mok Park , Semin Kwon , Jung Woo Leem , Vidhya Vijayakrishnan Nair , Yunjie Tong , Young L. Kim

To train the change detector, bi-temporal images taken at different times in the same area are used. However, collecting labeled bi-temporal images is expensive and time consuming. To solve this problem, various unsupervised change…

计算机视觉与模式识别 · 计算机科学 2022-04-06 Hyeoncheol Noh , Jingi Ju , Minseok Seo , Jongchan Park , Dong-Geol Choi

Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually…

计算机视觉与模式识别 · 计算机科学 2023-06-21 Shivam Pande , Nassim Ait Ali Braham , Yi Wang , Conrad M Albrecht , Biplab Banerjee , Xiao Xiang Zhu