Investigating Occlusion and Discretization Problems in Image-Based Blurring Techniques
Investigating Occlusion and Discretization Problems in Image-Based Blurring Techniques
复制标题
研究基于图像的模糊技术中的遮挡和离散化问题
DOI：
--
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
D. P. Chu
中科院分区：
文献类型：
--
作者：
B. Barsky;Michael J. Tobias;D. Horn;D. P. Chu
传统的计算机图形方法渲染的图像在所有深度上都显得清晰。添加模糊可以增加场景的真实感，提供比例感，并将观看者的注意力吸引到场景的特定区域。我们基于图像的模糊算法需要区分图像的一部分是来自单个对象还是多个对象的一部分。这激发了两种在图像渲染后识别对象的方法。我们说明了如何将这些技术与我们的图像空间方法结合使用来为场景添加模糊。
Traditional computer graphics methods render images that appear sharp at all depths. Adding blur can add realism to a scene, provide a sense of scale, and draw a viewer’s attention to a particular region of a scene. Our image based blur algorithm needs to distinguish whether a portion of an image is either from a single object or is part of more than one object. This motivates two approaches to identify objects after an image has been rendered. We illustrate how these techniques can be used in conjunction with our image space method to add blur to a scene.