中文
相关论文

相关论文: Fidelity-Naturalness Evaluation of Single Image Su…

200 篇论文

Super-resolution (SR) is an ill-posed inverse problem with a large set of feasible solutions that are consistent with a given low-resolution image. Various deterministic algorithms aim to find a single solution that balances fidelity and…

图像与视频处理 · 电气工程与系统科学 2024-02-13 Cansu Korkmaz , Ege Cirakman , A. Murat Tekalp , Zafer Dogan

Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions. Yet, the dominant paradigm is to employ pixel-wise losses, such as L_1, which drive…

计算机视觉与模式识别 · 计算机科学 2021-11-08 Andreas Lugmayr , Martin Danelljan , Fisher Yu , Luc Van Gool , Radu Timofte

Preserving accuracy is a challenging issue in super resolution images. In this paper, we propose a new FFT based image registration algorithm and a sparse based super resolution algorithm to improve the accuracy of super resolution image.…

计算机视觉与模式识别 · 计算机科学 2014-07-15 Archana Vijayan , Vincy Salam

Most current single image camera calibration methods rely on specific image features or user input, and cannot be applied to natural images captured in uncontrolled settings. We propose directly inferring camera calibration parameters from…

计算机视觉与模式识别 · 计算机科学 2018-04-24 Yannick Hold-Geoffroy , Kalyan Sunkavalli , Jonathan Eisenmann , Matt Fisher , Emiliano Gambaretto , Sunil Hadap , Jean-François Lalonde

Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both…

计算机视觉与模式识别 · 计算机科学 2019-12-04 Kekai Sheng , Weiming Dong , Menglei Chai , Guohui Wang , Peng Zhou , Feiyue Huang , Bao-Gang Hu , Rongrong Ji , Chongyang Ma

Super-resolution (SR) has become a widely researched topic in recent years. SR methods can improve overall image and video quality and create new possibilities for further content analysis. But the SR mainstream focuses primarily on…

计算机视觉与模式识别 · 计算机科学 2022-04-12 Eugene Lyapustin , Anastasia Kirillova , Viacheslav Meshchaninov , Evgeney Zimin , Nikolai Karetin , Dmitriy Vatolin

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning…

计算机视觉与模式识别 · 计算机科学 2022-07-14 Qiang Li , Zhaoliang Yao , Jingjing Wang , Ye Tian , Pengju Yang , Di Xie , Shiliang Pu

Subjective image quality metrics are usually evaluated according to the correlation with human opinion in databases with distortions that may appear in digital media. However, these oversee affine transformations which may represent better…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Nuria Alabau-Bosque , Paula Daudén-Oliver , Jorge Vila-Tomás , Valero Laparra , Jesús Malo

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Mingxiao Li , Tingyu Qu , Tinne Tuytelaars , Marie-Francine Moens

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak…

计算机视觉与模式识别 · 计算机科学 2018-01-16 Mehdi S. M. Sajjadi , Bernhard Schölkopf , Michael Hirsch

Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where…

图像与视频处理 · 电气工程与系统科学 2022-04-05 Shangqi Gao , Xiahai Zhuang

Recent years have shown an increased development of methods for justifying the predictions of neural networks through visual explanations. These explanations usually take the form of heatmaps which assign a saliency (or relevance) value to…

计算机视觉与模式识别 · 计算机科学 2024-02-20 Benjamin Vandersmissen , Jose Oramas

Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational…

计算机视觉与模式识别 · 计算机科学 2016-08-31 Carlos Miravet , Francisco B. Rodriguez

Image super-resolution models are commonly evaluated by average scores (over some benchmark test sets), which fail to reflect the performance of these models on images of varying difficulty and that some models generate artifacts on certain…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Atakan Topaloglu , Ahmet Bilican , Cansu Korkmaz , A. Murat Tekalp

Fairness has been a critical issue that affects the adoption of deep learning models in real practice. To improve model fairness, many existing methods have been proposed and evaluated to be effective in their own contexts. However, there…

机器学习 · 计算机科学 2024-03-26 Junjie Yang , Jiajun Jiang , Zeyu Sun , Junjie Chen

As super-resolution (SR) techniques advance, we observe a growing distrust of evaluation metrics in recent SR research. An inconsistency often emerges between certain evaluation criteria and human perceptual preference. Although current SR…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Shaolin Su , Josep M. Rocafort , Danna Xue , David Serrano-Lozano , Lei Sun , Javier Vazquez-Corral

Single-image high dynamic range (SI-HDR) reconstruction has recently emerged as a problem well-suited for deep learning methods. Each successive technique demonstrates an improvement over existing methods by reporting higher image quality…

计算机视觉与模式识别 · 计算机科学 2021-08-20 Gabriel Eilertsen , Saghi Hajisharif , Param Hanji , Apostolia Tsirikoglou , Rafal K. Mantiuk , Jonas Unger

Super-resolution (SR) is a technique that allows increasing the resolution of a given image. Having applications in many areas, from medical imaging to consumer electronics, several SR methods have been proposed. Currently, the best…

计算机视觉与模式识别 · 计算机科学 2019-12-02 Marija Vella , João F. C. Mota

Real-world Super-Resolution (SR) has been traditionally tackled by first learning a specific degradation model that resembles the noise and corruption artifacts in low-resolution imagery. Thus, current methods lack generalization and lose…

图像与视频处理 · 电气工程与系统科学 2021-08-27 Angela Castillo , María Escobar , Juan C. Pérez , Andrés Romero , Radu Timofte , Luc Van Gool , Pablo Arbeláez

Most existing super-resolution methods do not perform well in real scenarios due to lack of realistic training data and information loss of the model input. To solve the first problem, we propose a new pipeline to generate realistic…

图像与视频处理 · 电气工程与系统科学 2019-05-30 Xiangyu Xu , Yongrui Ma , Wenxiu Sun