摘要
產生深度圖的規則是依照畫面當中每一個物體的表面與觀看者所在的實際距離紀錄每一個像素的深度。同一物件內的深度資訊並不會相差太多。因此，為了從單一張二維影像中取得深度圖，我們從畫面中的物件及紋路開始著手是合理的。我們先針對整張影像計算，求出消失點(Vanishing Point)的位置，並假設消失點是距離觀看者最遠的一點，因此越接近消失點的物件，我們賦予較深的深度值，反之亦然。在取得物件切割方面，我們提出以顏色為基礎的切割方式。產生深度圖之後，就可以依照深度圖對原本的影像加以變形，產生看似多個不同視角拍攝的影像(Multi-View)。在產生多視角影像之前，我們額外再對每一個像素的深度值轉換成人類可以接受的深度知覺，多加了這個轉換步驟是為了要在之後的影像變形(Image Warping)時減少破洞的產生。最後在以我們新提出的擬真形變方法產生多重視角影像。稱為栩栩如生影像三維形變(Vivid-DIBR)，與傳統的三維形變差異在於，考慮到人類視覺的感受，因此我們提出一個新的轉換公式，我們使形變後的影像，以聚焦平面為基礎，將前景和後景分開並且反向計算，滿足實際情形，三維顯示器表面如同聚焦平面，而前景看似突出螢幕，後景如同內陷於螢幕之中，滿足觀測者的立體視覺。如此，二維圖像經過我們的系統後，即可以產生多視角影像，並且放到三維顯示器使用，產生可觀賞的立體影像。
並列摘要
The multiview perspectives are captured around a scene by camera array at the same time, and multi-view images can not only keep two dimensions information but also have the depth architecture of a scene. Most of 3D displays support the multi-view contents, while there is a bottleneck of 3D TV system to broadcast the larger storage and bandwidth for end-user. For saving bandwidth, a new TV broadcasting channel transfers third dimensional information i.e. depth map has been utilized. The 3D display renders intermediate image and a depth map to form different views, as well as synthesizes these images into one image; this technology is the renowned DIBR (Depth Image Base Rendering.) In other word, any 2D contents can be transformed into multi-view images according to their corresponding depth map. Our system processes 2D image to capture a depth map of the intermediate view image during 3D contents capturing. We utilize the vanishing point detection and color image segmentation technique to find the objects and deepest point (i.e. vanishing point) in the image, and then we assign depth value by comparing the vanishing point of object with image. After depth map generation, we propose the Vivid-DIBR system to imitate how human eyes see things. On the other hand, this system solves the holes (warping error points) problem by redistributing corresponding depth map. We implement the Vivid-DIBR by cell-based design flow and the 0.18um 1P6M implementation process of Taiwan Semiconductor Manufacturing Company. The design aims to convert 2D images into multi-view images which will be suitable for any interlacing 3D display by adjusting the focal plane location.