期刊文献+

数字地球渲染中单精度浮点数误差改正 被引量:5

Correction method of single-precision floating-point error for digita Earth rendering
原文传递
导出
摘要 目的针对全球大场景渲染中单精度浮点数的低精度导致的图像抖动和撕裂问题,提出了一套完整的解决方法。方法首先,使用全球四叉树结构来寻找新的坐标原点,避免了现有算法需要频繁切换世界坐标原点的缺点;其次,在新坐标系下进行坐标转换和矩阵转换,解决了像素坐标计算的误差导致的抖动问题;最后,在GPU中使用基于对数的深度计算方式来提高深度的分辨率,解决了深度计算误差导致的Z-Fighting现象。结果实验结果表明所提方法能很好地解决单精度浮点导致的渲染问题。结论此方法具有适应性强、实现复杂度低、精度和效率可控等优点。 Objective To solve the jitter and tear problems caused by single-precision floating-point errors in global scene rendering, a complete set of solutions is presented. Method First, a new coordinate origins is found by using the global quad-tree structure, avoiding the disadvantages of switching coordinate origins frequently; Second, the jitter problem is solved by transforming the coordinate and matrix in the new coordinate system; finally, the depth resolution is improved by using logarithmic calculation on the GPU, and the Z-Fighting problem is solved. Result The experiment results show that the proposed method can be a good solution to the problem caused by single-precision floating-point errors. Conclusion It has strong adaptability, low complexity, and it is controllable with accuracy and efficiency advantages.
出处 《中国图象图形学报》 CSCD 北大核心 2014年第1期119-125,共7页 Journal of Image and Graphics
基金 国家自然科学基金项目(61070124) 安徽省自然科学基金项目(1208085MF107) 安徽省高等学校省级自然科学研究重点项目(KJ2012A221)
关键词 全球场景 GPU渲染 变坐标 全球四叉树 深度计算 global scene GPU rendering dynamic coordinate system global quad-tree depth calculation
  • 相关文献

参考文献15

  • 1Goldberg D. What every computer scientist should know about floating-point arithmetic[J].ACM Computing Surveys (CSUR),1991,(1):5-48.
  • 2Akeley K,Su J. Minimum triangle separation for correct z-buffer occlusion[A].Vienna,Austria:ACM,2006.27-30.
  • 3Nickolls J,Dally W J. The GPU computing era[J].{H}IEEE MICRO,2010,(2):56-69.
  • 4Whitehead N,Fit-Florea A. Precision & performance:floating point and IEEE 754 compliance for NVIDIA GPUs,White Paper[R].Santa Clara,USA:NVIDIA Corporation,2011.
  • 5Priest D M. Algorithms for arbitrary precision floating point arithmetic[A].Grenoble:IEEE,1991.132-143.
  • 6Thall A. Extended-precision floating-point numbers for GPU computation[A].New York:ACM,2006.52.
  • 7Lindstrom P,Koller D,Ribarsky W. An integrated global GIS and visual simulation system,GIT-GVU-97-07[R].Atlanta,USA:Georgia Institute of Technology,1997.
  • 8郑娟,姜振东.空间战场可视化系统的设计与实现[J].计算机仿真,2005,22(1):36-39. 被引量:10
  • 9汪荣峰,廖学军.大尺度空间场景可视化中浮点精度问题研究[J].计算机工程,2011,37(16):276-278. 被引量:1
  • 10O'Neil S. A real-time procedural universe[EB/OL].http://www.gamasutra.com/features/20010302/oneil_ 01.htm,2005,2001.

二级参考文献21

  • 1吴恩华.图形处理器用于通用计算的技术、现状及其挑战[J].软件学报,2004,15(10):1493-1504. 被引量:141
  • 2郑娟,姜振东.空间战场可视化系统的设计与实现[J].计算机仿真,2005,22(1):36-39. 被引量:10
  • 3杜莹,武玉国,王晓明,游雄.全球多分辨率虚拟地形环境的金字塔模型研究[J].系统仿真学报,2006,18(4):955-958. 被引量:35
  • 4Lambers M, Kolb A. GPU-Based Framework for Distributed Interactive 3D Visualization of Multimodal Remote Sensing Data [C]//Proc. Int. IEEE Geoseience and Remote Sensing Symposium (IGARSS). 2009. USA: IEEE, 2009.
  • 5Chapra C, Canale RP. Numerical Methods for Engineers [M]. USA: McGraw-Hill, 2006, 63-65.
  • 6Wikipedia. IEEE 754 [EB/OL]. (2011-2-5) [2011-2-12]. http://en.wikipedia.org/wiki/Floating_oint.
  • 7Wikipedia. Round-off error [EB/OL]. (2011-2-3) [2011-2-12]. http://en.wikipedia.org/wiki/Round-off.
  • 8Alexey Barkovoy. Pixel Shader 2.0 precision [EB/OL]. (2010) [2010-9-28]. 2010. http://www.digit-life.com/articles2/ps-precision.
  • 9Thorne C. Origin-centric Techniques for Optimising Scalability and the Fidelity of Motion, Interaction and Rendering [D]. Perth, Australia: University of Western Australia, 2007: 30-31.
  • 10Lindstrom P, Koller D, Ribarsky W, Hodges LF, Bosch A, Faust N An integrated global GIS and visual simulation system [R]//Tech Rep. GIT-GVU-97-07. USA: Georgia Institute of Technology, March, 1997.

共引文献11

同被引文献31

引证文献5

二级引证文献17

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部