Results 271 to 280 of about 216,992 (320)

Self-adaptive blind super-resolution image reconstruction

2010 3rd International Congress on Image and Signal Processing, 2010
Super-resolution (SR) image reconstruction is a rapidly developing area in image processing. Especially, blind SR can generate high space resolution image without requiring priori information of the point spread function (PSF). In this paper, we propose a self-adaptive blind super-resolution image reconstruction approach which is based on multiple ...
Yunfei Bai, Jing Hu, Yupin Luo
openaire   +1 more source

EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution

arXiv.org
Utilizing pre-trained Text-to-Image (T2I) diffusion models to guide Blind Super-Resolution (BSR) has become a predominant approach in the field. While T2I models have traditionally relied on U-Net architectures, recent advancements have demonstrated that
Haizhen Xie, Kunpeng Du, Qi Yan, Sen Lu, Jianhong Han, Hanting Chen, Hailin Hu, Jie Hu   +7 more
semanticscholar   +1 more source

Blind Super-resolution for Single Image Reconstruction

2010 Fourth Pacific-Rim Symposium on Image and Video Technology, 2010
Image super-resolution reconstructions (SR) require image degradation model (DM) as the prior, however, the actual DM is often unknown in practical applications. In this work, a novel framework is proposed for single image SR, where the explicit DM is unknown.
Fei Han, Xiangzhong Fang, Ci Wang
openaire   +1 more source

DC-Mamba: A Degradation-Aware Cross-Modality Framework for Blind Super-Resolution of Thermal UAV Images

IEEE Transactions on Geoscience and Remote Sensing
The low-resolution thermal imaging from uncrewed aerial vehicles (UAVs) poses a substantial obstacle to the understanding and analysis of ground targets.
Pengju Si, Miao Jia, Huan Wang, Jun Wang, Lifan Sun, Zhumu Fu   +5 more
semanticscholar   +1 more source

Degradation-aware dynamic kernel for blind super-resolution

Imaging Science Journal
Image super-resolution (SR) methods based on convolutional neural networks have become mainstream. However, unknown degradation in test images significantly affects SR performance.
L. Fu, Yang Liao, Zengfa Dou, Yun Bai, Guangjun Liu, Xi Zhao   +5 more
semanticscholar   +1 more source

KernelFusion: Assumption-Free Blind Super-Resolution via Patch Diffusion

arXiv.org
Traditional super-resolution (SR) methods assume an ``ideal'' downscaling SR-kernel (e.g., bicubic downscaling) between the high-resolution (HR) image and the low-resolution (LR) image.
Oliver Heinimann, Assaf Shocher, Tal Zimbalist, Michal Irani   +3 more
semanticscholar   +1 more source

A VQ-Based Blind Super-Resolution Algorithm

2005
In this paper, a novel method of blind Super-Resolution (SR) image restoration is presented. First, a learning based blur identification method is proposed to identify the blur parameter in which Sobel operator and Vector Quantization (VQ) are used for extracting feature vectors.
Jianping Qiao, Ju Liu, Guoxia Sun
openaire   +1 more source

Nonparametric Blind Super-Resolution Using Adaptive Heavy-Tailed Priors

Journal of Mathematical Imaging and Vision, 2019
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Shao, Wen-Ze, Ge, Qi, Wang, Li-Qian, Lin, Yun-Zhi, Deng, Hai-Song, Li, Hai-Bo   +5 more
openaire   +2 more sources

Dynamic Degradation Intensity Estimation for Adaptive Blind Super-Resolution: A Novel Approach and Benchmark Dataset

IEEE transactions on circuits and systems for video technology (Print)
Blind Super-Resolution (BlindSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) images without prior knowledge of the image degradation process. This is a challenging problem in real-world applications, where the degradation can
Guang-yong Chen, Wu-Ding Weng, Jiannan Su, Senior Member Ieee Min Gan, F. I. C. L. Philip Chen   +4 more
semanticscholar   +1 more source

Blind super-resolution of sparse spike signals

2015 49th Asilomar Conference on Signals, Systems and Computers, 2015
In many applications, the observations can be modeled as a linear combination of a small number of scaled and shifted copies of a bandlimited point spread function, either determined by the nature or designed by the users. Examples include neural spike trains, returns in radar and sonar, images in astronomy and single-molecule microscopy, etc. It is of
openaire   +1 more source