用CNN预测图像视频的隐含分辨率，准确率达95%
Latent Image and Video Resolution Prediction using Convolutional Neural Networks
- 构建新数据集并提出基于CNN的隐含分辨率预测方法
- 在真实数据上实现约95%的分辨率预测准确率
- 适合图像修复、画质评估等领域的研究者参考
本文提出一个尚未受到充分关注的视频质量评估问题——隐含分辨率预测。当图像或视频从原始分辨率缩放后，其报告分辨率可能高于实际原始分辨率。本文定义该问题，构建用于训练与评估的数据集，并引入多种机器学习算法，包括两种卷积神经网络（CNN）来解决此问题。实验表明，部分所提方法可在该任务上达到约95%的准确率。
原文摘要 · Abstract (English)
This paper introduces a Video Quality Assessment (VQA) problem that has received little attention in the literature, called the latent resolution prediction problem. The problem arises when images or videos are upscaled from their native resolution and are reported as having a higher resolution than their native resolution. This paper formulates the problem, constructs a dataset for training and evaluation, and introduces several machine learning algorithms, including two Convolutional Neural Networks (CNNs), to address this problem. Experiments indicate that some proposed methods can predict the latent video resolution with about 95% accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。