中文
相关论文

相关论文: Exploring Semantic Feature Discrimination for Perc…

200 篇论文

Generative Adversarial Networks (GANs) have been widely used to recover vivid textures in image super-resolution (SR) tasks. In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world…

图像与视频处理 · 电气工程与系统科学 2024-03-01 Bingchen Li , Xin Li , Hanxin Zhu , Yeying Jin , Ruoyu Feng , Zhizheng Zhang , Zhibo Chen

Generative adversarial network (GAN) for image super-resolution (SR) has attracted enormous interests in recent years. However, the GAN-based SR methods only use image discriminator to distinguish SR images and high-resolution (HR) images.…

计算机视觉与模式识别 · 计算机科学 2020-03-18 Xuan Zhu , Yue Cheng , Jinye Peng , Rongzhi Wang , Mingnan Le , Xin Liu

Face super-resolution is a domain-specific image super-resolution, which aims to generate High-Resolution (HR) face images from their Low-Resolution (LR) counterparts. In this paper, we propose a novel face super-resolution method, namely…

计算机视觉与模式识别 · 计算机科学 2023-01-04 Xiang Wang , Yimin Yang , Qixiang Pang , Xiao Lu , Yu Liu , Shan Du

No-reference image quality assessment (NR-IQA) aims to simulate the process of perceiving image quality aligned with subjective human perception. However, existing NR-IQA methods either focus on global representations that leads to limited…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Chenyue Song , Chen Hui , Haiqi Zhu , Feng Jiang , Yachun Mi , Wei Zhang , Shaohui Liu

Super-resolution (SR), a classical inverse problem in computer vision, is inherently ill-posed, inducing a distribution of plausible solutions for every input. However, the desired result is not simply the expectation of this distribution,…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Fengjia Zhang , Samrudhdhi B. Rangrej , Tristan Aumentado-Armstrong , Afsaneh Fazly , Alex Levinshtein

The traditional super-resolution methods that aim to minimize the mean square error usually produce the images with over-smoothed and blurry edges, due to the lose of high-frequency details. In this paper, we propose two novel techniques in…

图像与视频处理 · 电气工程与系统科学 2020-12-25 Yitong Yan , Chuangchuang Liu , Changyou Chen , Xianfang Sun , Longcun Jin , Xiang Zhou

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we…

There has been a growing interest in developing image super-resolution (SR) algorithms that convert low-resolution (LR) to higher resolution images, but automatically evaluating the visual quality of super-resolved images remains a…

计算机视觉与模式识别 · 计算机科学 2022-07-19 Wei Zhou , Zhou Wang

Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…

计算机视觉与模式识别 · 计算机科学 2020-09-14 Zheng Hui , Jie Li , Xinbo Gao , Xiumei Wang

Fine-Grained Visual Classification (FGVC) is known as a challenging task due to subtle differences among subordinate categories. Many current FGVC approaches focus on identifying and locating discriminative regions by using the attention…

计算机视觉与模式识别 · 计算机科学 2023-02-22 Hui Wang , Yueyang li , Haichi Luo

Text-to-image synthesis aims to generate a photo-realistic image from a given natural language description. Previous works have made significant progress with Generative Adversarial Networks (GANs). Nonetheless, it is still hard to generate…

计算机视觉与模式识别 · 计算机科学 2021-09-03 Eunyeong Jeon , Kunhee Kim , Daijin Kim

While most existing segmentation methods usually combined the powerful feature extraction capabilities of CNNs with Conditional Random Fields (CRFs) post-processing, the result always limited by the fault of CRFs . Due to the notoriously…

计算机视觉与模式识别 · 计算机科学 2021-04-21 ZengShun Zhaoa , Yulong Wang , Ke Liu , Haoran Yang , Qian Sun , Heng Qiao

The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper, we propose to…

计算机视觉与模式识别 · 计算机科学 2019-04-22 Zihan Ye , Fan Lyu , Linyan Li , Qiming Fu , Jinchang Ren , Fuyuan Hu

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Xudong Li , Timin Gao , Runze Hu , Yan Zhang , Shengchuan Zhang , Xiawu Zheng , Jingyuan Zheng , Yunhang Shen , Ke Li , Yutao Liu , Pingyang Dai , Rongrong Ji

In this work, we introduce Gradient Siamese Network (GSN) for image quality assessment. The proposed method is skilled in capturing the gradient features between distorted images and reference images in full-reference image quality…

图像与视频处理 · 电气工程与系统科学 2022-08-09 Heng Cong , Lingzhi Fu , Rongyu Zhang , Yusheng Zhang , Hao Wang , Jiarong He , Jin Gao

Semantic segmentation relies on many dense pixel-wise annotations to achieve the best performance, but owing to the difficulty of obtaining accurate annotations for real world data, practitioners train on large-scale synthetic datasets.…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Cristina Mata , Michael S. Ryoo , Henrik Turbell

Most existing face image Super-Resolution (SR) methods assume that the Low-Resolution (LR) images were artificially downsampled from High-Resolution (HR) images with bicubic interpolation. This operation changes the natural image…

计算机视觉与模式识别 · 计算机科学 2021-02-08 Andreas Aakerberg , Kamal Nasrollahi , Thomas B. Moeslund

This work addresses the problems of semantic segmentation and image super-resolution by jointly considering the performance of both in training a Generative Adversarial Network (GAN). We propose a novel architecture and domain-specific…

计算机视觉与模式识别 · 计算机科学 2022-05-19 Tristan Frizza , Donald G. Dansereau , Nagita Mehr Seresht , Michael Bewley

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed…

计算机视觉与模式识别 · 计算机科学 2021-07-21 Wenlong Zhang , Yihao Liu , Chao Dong , Yu Qiao

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…

计算机视觉与模式识别 · 计算机科学 2023-11-01 Royson Lee , Rui Li , Stylianos I. Venieris , Timothy Hospedales , Ferenc Huszár , Nicholas D. Lane
‹ 上一页 1 2 3 10 下一页 ›