检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:李健宽 LI Jian-kuan(College of Computer Science,Sichuan University,Chengdu 610065)
出 处:《现代计算机》2020年第10期85-88,共4页Modern Computer
摘 要:图形反走样算法是实时渲染领域中一种缓解几何边缘锯齿、纹理失真,带来高质量图形渲染效果的方法。近年越来越多的深度学习方法被用在实时渲染中,但现有的主流时域反走样算法,未涉及到与深度学习的结合。将时域反走样的流程与循环神经网络相结合,提出一种新的反走样算法,通过神经网络完成时域反走样中的历史样本颜色融合过程,改善现有的时域反走样效果。Anti-aliasing is aim at avoiding aliasing artifacts caused by low sampling rate,which leads to high quality images in real-time rendering.In recent years,more and more deep learning methods have been applied to computer graphics.However,deep learning approach has not been applied to temporal anti-aliasing.In this paper,we proposed a new anti-aliasing method,which replace the heuristic approach in tem poral anti-aliasing with deep learning approach.The result shows the proposed method provides a sufficient way to weaken the aliasing problem.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38