中文
相关论文

相关论文: Semantic-embedded Unsupervised Spectral Reconstruc…

200 篇论文

Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Zhiwen Fan , Jian Zhang , Wenyan Cong , Peihao Wang , Renjie Li , Kairun Wen , Shijie Zhou , Achuta Kadambi , Zhangyang Wang , Danfei Xu , Boris Ivanovic , Marco Pavone , Yue Wang

Displaying the large number of bands in a hyper- spectral image (HSI) on a trichromatic monitor is important for HSI processing and analysis system. The visualized image shall convey as much information as possible from the original HSI and…

计算机视觉与模式识别 · 计算机科学 2017-12-06 Danping Liao , Yuntao Qian , Yuan Yan Tang

We consider the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable. Different from traditional super-resolution formulation, the low-resolution…

计算机视觉与模式识别 · 计算机科学 2018-09-05 Yuan Yuan , Siyuan Liu , Jiawei Zhang , Yongbing Zhang , Chao Dong , Liang Lin

The progress on Hyperspectral image (HSI) super-resolution (SR) is still lagging behind the research of RGB image SR. HSIs usually have a high number of spectral bands, so accurately modeling spectral band interaction for HSI SR is hard.…

计算机视觉与模式识别 · 计算机科学 2024-09-16 Ke Li , Luc Van Gool , Dengxin Dai

We propose a self-supervised method for image relighting of single view images in the wild. The method is based on an auto-encoder which deconstructs an image into two separate encodings, relating to the scene illumination and content,…

计算机视觉与模式识别 · 计算机科学 2021-08-24 Yang Liu , Alexandros Neophytou , Sunando Sengupta , Eric Sommerlade

In this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network. The network takes an RGB image as input, regresses…

计算机视觉与模式识别 · 计算机科学 2021-02-15 Ye Yu , William A. P. Smith

Modern cameras typically offer two types of image states: a minimally processed linear raw RGB image representing the raw sensor data, and a highly-processed non-linear image state, such as the sRGB state. The CIE-XYZ color space is a…

图像与视频处理 · 电气工程与系统科学 2024-05-22 Shir Barzel , Moshe Salhov , Ofir Lindenbaum , Amir Averbuch

Recently, deep learning-based single image reflection separation methods have been exploited widely. To benefit the learning approach, a large number of training image pairs (i.e., with and without reflections) were synthesized in various…

计算机视觉与模式识别 · 计算机科学 2020-10-01 Soomin Kim , Yuchi Huo , Sung-Eui Yoon

Single image super-resolution (SR) is an ill-posed problem which aims to recover high-resolution (HR) images from their low-resolution (LR) observations. The crux of this problem lies in learning the complex mapping between low-resolution…

计算机视觉与模式识别 · 计算机科学 2017-01-05 Ding Liu , Zhaowen Wang , Nasser Nasrabadi , Thomas Huang

In this paper, we tackle the problem of enhancing real-world low-light images with significant noise in an unsupervised fashion. Conventional unsupervised learning-based approaches usually tackle the low-light image enhancement problem…

图像与视频处理 · 电气工程与系统科学 2022-03-29 Wei Xiong , Ding Liu , Xiaohui Shen , Chen Fang , Jiebo Luo

All-in-one image restoration tasks are becoming increasingly important, especially for ultra-high-definition (UHD) images. Existing all-in-one UHD image restoration methods usually boost the model's performance by introducing prompt or…

计算机视觉与模式识别 · 计算机科学 2024-08-14 Xin Su , Zhuoran Zheng , Chen Wu

In this paper, we tackle a fully unsupervised super-resolution problem, i.e., neither paired images nor ground truth HR images. We assume that low resolution (LR) images are relatively easy to collect compared to high resolution (HR)…

计算机视觉与模式识别 · 计算机科学 2020-04-24 Namhyuk Ahn , Jaejun Yoo , Kyung-Ah Sohn

Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in…

计算机视觉与模式识别 · 计算机科学 2022-04-26 Tsung-Wei Ke , Jyh-Jing Hwang , Yunhui Guo , Xudong Wang , Stella X. Yu

One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image…

计算机视觉与模式识别 · 计算机科学 2016-07-27 Yifan Wang , Lijun Wang , Hongyu Wang , Peihua Li

Many of the existing methods for learning joint embedding of images and text use only supervised information from paired images and its textual attributes. Taking advantage of the recent success of unsupervised learning in deep neural…

计算机视觉与模式识别 · 计算机科学 2017-03-21 Yao-Hung Hubert Tsai , Liang-Kang Huang , Ruslan Salakhutdinov

Single image super resolution (SR), which refers to reconstruct a higher-resolution (HR) image from the observed low-resolution (LR) image, has received substantial attention due to its tremendous application potentials. Despite the…

计算机视觉与模式识别 · 计算机科学 2017-08-01 Yukai Shi , Keze Wang , Chongyu Chen , Li Xu , Liang Lin

Depth reconstruction and hyperspectral reflectance reconstruction are two active research topics in computer vision and image processing. Conventionally, these two topics have been studied separately using independent imaging setups and…

计算机视觉与模式识别 · 计算机科学 2022-04-11 Chunyu Li , Yusuke Monno , Masatoshi Okutomi

Applying data-driven approaches to non-rigid 3D reconstruction has been difficult, which we believe can be attributed to the lack of a large-scale training corpus. Unfortunately, this method fails for important cases such as highly…

计算机视觉与模式识别 · 计算机科学 2020-06-23 Aljaž Božič , Michael Zollhöfer , Christian Theobalt , Matthias Nießner

We present a novel method to reconstruct a spectral central view and its aligned disparity map from spatio-spectrally coded light fields. Since we do not reconstruct an intermediate full light field from the coded measurement, we refer to…

计算机视觉与模式识别 · 计算机科学 2021-10-15 Maximilian Schambach , Jiayang Shi , Michael Heizmann

This work studies Hyperspectral image (HSI) super-resolution (SR). HSI SR is characterized by high-dimensional data and a limited amount of training examples. This exacerbates the undesirable behaviors of neural networks such as…

计算机视觉与模式识别 · 计算机科学 2021-04-06 Ke Li , Dengxin Dai , Ender Konukoglu , Luc Van Gool