中文
相关论文

相关论文: Continuous Degradation Modeling via Latent Flow Ma…

200 篇论文

Most super-resolution (SR) models struggle with real-world low-resolution (LR) images. This issue arises because the degradation characteristics in the synthetic datasets differ from those in real-world LR images. Since SR models are…

图像与视频处理 · 电气工程与系统科学 2025-03-05 Ru Ito , Supatta Viriyavisuthisakul , Kazuhiko Kawamoto , Hiroshi Kera

Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution (LR) and…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Hongyang Zhou , Xiaobin Zhu , Liuling Chen , Junyi He , Jingyan Qin , Xu-Cheng Yin , Zhang xiaoxing

Super-resolution (SR) has traditionally been based on pairs of high-resolution images (HR) and their low-resolution (LR) counterparts obtained artificially with bicubic downsampling. However, in real-world SR, there is a large variety of…

图像与视频处理 · 电气工程与系统科学 2020-11-06 Mohammad Saeed Rad , Thomas Yu , Claudiu Musat , Hazim Kemal Ekenel , Behzad Bozorgtabar , Jean-Philippe Thiran

Most learning-based super-resolution (SR) methods aim to recover high-resolution (HR) image from a given low-resolution (LR) image via learning on LR-HR image pairs. The SR methods learned on synthetic data do not perform well in…

图像与视频处理 · 电气工程与系统科学 2020-01-09 Dong Gong , Wei Sun , Qinfeng Shi , Anton van den Hengel , Yanning Zhang

Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e.g., bicubic downsampling. As existing methods typically learn…

图像与视频处理 · 电气工程与系统科学 2021-09-09 Sanghyun Son , Jaeha Kim , Wei-Sheng Lai , Ming-Husan Yang , Kyoung Mu Lee

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing…

计算机视觉与模式识别 · 计算机科学 2024-09-30 Wanjie Sun , Zhenzhong Chen

Deep Convolution Neural Networks (CNN) have achieved significant performance on single image super-resolution (SR) recently. However, existing CNN-based methods use artificially synthetic low-resolution (LR) and high-resolution (HR) image…

计算机视觉与模式识别 · 计算机科学 2018-12-14 Tianyu Zhao , Wenqi Ren , Changqing Zhang , Dongwei Ren , Qinghua Hu

The state of the art in video super-resolution (SR) are techniques based on deep learning, but they perform poorly on real-world videos (see Figure 1). The reason is that training image-pairs are commonly created by downscaling a…

计算机视觉与模式识别 · 计算机科学 2021-05-07 Noam Elron , Alex Itskovich , Shahar S. Yuval , Noam Levy

Recent years have witnessed the great advances of deep neural networks (DNNs) in light field (LF) image super-resolution (SR). However, existing DNN-based LF image SR methods are developed on a single fixed degradation (e.g., bicubic…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Yingqian Wang , Zhengyu Liang , Longguang Wang , Jungang Yang , Wei An , Yulan Guo

Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data…

图像与视频处理 · 电气工程与系统科学 2023-05-05 Mehran Jeelani , Sadbhawna , Noshaba Cheema , Klaus Illgner-Fehns , Philipp Slusallek , Sunil Jaiswal

The current existing deep image super-resolution methods usually assume that a Low Resolution (LR) image is bicubicly downscaled of a High Resolution (HR) image. However, such an ideal bicubic downsampling process is different from the real…

计算机视觉与模式识别 · 计算机科学 2022-10-20 Rao Muhammad Umer , Christian Micheloni

Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent space. A potential limitation of these methods is that they…

计算机视觉与模式识别 · 计算机科学 2022-07-27 Fengjun Li , Xin Feng , Fanglin Chen , Guangming Lu , Wenjie Pei

The performance of deep learning based image super-resolution (SR) methods depend on how accurately the paired low and high resolution images for training characterize the sampling process of real cameras. Low and high resolution…

图像与视频处理 · 电气工程与系统科学 2022-06-22 Yanhui Guo , Xiaolin Wu , Xiao Shu

Current learning-based single image super-resolution (SISR) algorithms underperform on real data due to the deviation in the assumed degrada-tion process from that in the real-world scenario. Conventional degradation processes consider…

图像与视频处理 · 电气工程与系统科学 2022-02-14 Zhenxing Dong , Hong Cao , Wang Shen , Yu Gan , Yuye Ling , Guangtao Zhai , Yikai Su

In real-world single image super-resolution (SISR) task, the low-resolution image suffers more complicated degradations, not only downsampled by unknown kernels. However, existing SISR methods are generally studied with the synthetic…

图像与视频处理 · 电气工程与系统科学 2020-09-15 Guanghao Yin , Shouqian Sun , Chao Li , Xin Min

Diffusion models (DMs) have demonstrated remarkable success in real-world image super-resolution (SR), yet their reliance on time-consuming multi-step sampling largely hinders their practical applications. While recent efforts have…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Jiaqi Xu , Wenbo Li , Haoze Sun , Fan Li , Zhixin Wang , Long Peng , Jingjing Ren , Haoran Yang , Xiaowei Hu , Renjing Pei , Pheng-Ann Heng

Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i.e., bicubic…

计算机视觉与模式识别 · 计算机科学 2019-04-02 Jianrui Cai , Hui Zeng , Hongwei Yong , Zisheng Cao , Lei Zhang

Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these…

图像与视频处理 · 电气工程与系统科学 2021-10-22 Rui Ma , Johnathan Czernik , Xian Du

For image super-resolution (SR), bridging the gap between the performance on synthetic datasets and real-world degradation scenarios remains a challenge. This work introduces a novel "Low-Res Leads the Way" (LWay) training framework,…

图像与视频处理 · 电气工程与系统科学 2024-03-06 Haoyu Chen , Wenbo Li , Jinjin Gu , Jingjing Ren , Haoze Sun , Xueyi Zou , Zhensong Zhang , Youliang Yan , Lei Zhu

Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather the paired training data by synthesizing LR images from HR…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Zeshuai Deng , Zhuokun Chen , Shuaicheng Niu , Thomas H. Li , Bohan Zhuang , Mingkui Tan
‹ 上一页 1 2 3 10 下一页 ›