...
首页> 外文期刊>Computer Animation and Virtual Worlds >Stereoscopic image generation of background terrain scenes
【24h】

Stereoscopic image generation of background terrain scenes

机译:背景地形场景的立体图像生成

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

The reconstruction of 3D terrain geometry from images is essential for compositing CG objects into a live-actionnbackground or for 2D to 3D conversion of terrain scenes.We present a novel mesh refinement algorithm for the creation ofnstereoscopic images of terrain scenes. Previous approaches emphasise the smoothness of the resulting terrain mesh overnaccuracy [1]. Point cloud-based methods cannot effectively recover the entire surface, leading to visual discrepancies afternmonocular sequences are converted into 3D stereo. As misalignment or inaccurate 3D terrain data over corresponding 2Dnbackground images can result in visual fatigue when stereo sequences are generated, ensuring accuracy of the reconstructedngeometry is very important. To achieve the necessary accuracy, our method evaluates mesh errors utilising a texturenprojection onto the geometry and refines the mesh using Laplacian-based editing. Our algorithm automatically generatesnstereoscopic images of terrain scenes. In addition, our method simplifies identification and compositing of foregroundnobjects on the terrain geometry. Copyright # 2011 John Wiley & Sons, Ltd.
机译:从图像重建3D地形几何对于将CG对象合成为真实背景或2D到3D地形场景转换至关重要。我们提出了一种新颖的网格优化算法,用于创建地形场景的立体图像。先前的方法强调了导致的地形网格误差的平滑性[1]。基于点云的方法无法有效地恢复整个表面,从而导致将单眼序列转换为3D立体后出现视觉差异。当生成立体序列时,由于对应2Dnbackground图像上的未对准或不准确的3D地形数据可能导致视觉疲劳,因此确保重构几何的准确性非常重要。为了达到必要的精度,我们的方法利用纹理投影到几何上来评估网格误差,并使用基于拉普拉斯算子的编辑来细化网格。我们的算法会自动生成地形场景的立体图像。另外,我们的方法简化了地形几何上前景对象的识别和合成。版权所有©2011 John Wiley&Sons,Ltd.

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号