ID 原文 译文
56108 算法以边缘和距离为约束,在每个像素的邻近区域上构造一张对邻域上像素点拟合的二次多项式曲面片,并在每个四边形网格上构造一张二次多项式中间曲面片. The algorithm constructs a quadratic polynomial surface patch on the adjacentregion of each pixel, which fits the pixels in the neighborhood, and a quadratic polynomial median surface patch isconstructed on each quadrilateral mesh.
56109 在每个四边形网格上由五张曲面片加权平均生成有理多项式曲面片. The rational polynomial patch is generated from the weighted average offive patches on each quadrilateral mesh.
56110 该曲面片具有二次多项式逼近精度,产生的图像具有较好的视觉效果.通过构造误差曲面片对二次多项式曲面片进行修正,提高了放大图像的精度和视觉效果. The patch has the accuracy of the quadratic polynomial approximation,and the resulting image has a better visual effect.
56111 新算法把二次多项式的常数项、一次和二次项采用不同方法分别计算,为构造带约束的多项式函数提供了新技术. The accuracy and visual effects of the magnified image areimproved by constructing error patches.
56112 实验结果表明,相比于其他算法,本文算法不仅有较高的逼近精度,而且放大图像的视觉效果也较好. The new algorithm calculates the constant term, the first term and thesecond term of the quadratic polynomial by different methods, which provides a new technique for constructing thepolynomial function with constraints. The experimental results show that compared with other algorithms, theproposed algorithm not only has higher approximation accuracy but also has better visual effect of the magnifiedimage.
56113 在计算机视觉中,群体分析越来越受到人们的关注,对图像中复杂人群进行分组是群体分析领域的基础技术需求. In computer vision, more attention has been paid to group analysis, and the group detection inimages becomes a key technology of human analysis on groups.
56114 现有的人群社交分组方法只针对固定人数的小范围场景,不能处理真实世界中的大场景图像. The existing social grouping methods only focuson small scenes with fixed number of persons and cannot deal with large scene images in the real world.
56115 本文提出首个面向十亿像素大场景图像的基于深度学习的细粒度人群社交分组框架,由一种图引导的全局到局部的划分策略与一个学习隐函数表示社交对交互模式的深度社交分组网络组成. Thispaper proposes the first fine-grained social grouping framework for gigapixel large scene images based on deeplearning, which consists of a graph-guided global-to-local partition strategy and a deep grouping network thatlearns an implicit respresentation for social pairs.
56116 该框架可在大范围场景图像上实现准确的人群分组. The framework has achieved accurate grouping on large sceneimages.
56117 本文方法同样适用于小场景图像,在小场景图像数据集上的实验结果表明,本文提出的框架相比于现有方法取得了显著的性能提升. Our method is also applicable to small scene images, and has outperformed the existing methods.