- 學位論文
模擬相片於不同光源及材質下成像之一致性紋理生成
Coherent Texture Synthesis for Photograph Relighting and Texture Transfer
摘要
在這篇碩士論文中，我們提出了一個紋理合成的方法，不需要真實的物理反射模型，而得以實現擬真的材質繪圖。這個方法是藉由觀察現實生活中的物體都含有某種紋理重複的出現在物體的表面，而這些重複出現的紋理可以形成一個較為稀疏的紋理函數模型。我們的目標是利用拍攝不同光源的照片來還原出物體所隱含的材質及可能的物理反射特性。這個方法不需要複雜的儀器來拍攝，並且利用紋理生成的方法還原一個近似的紋理函數模型。 我們的輸入是多張拍攝的影像。這些照片的視角是固定的，不同的只是光源的方向。我們利用Photometric Stereo來估計物體的幾何形狀及物體本身的顏色。並且把物體上的每個點根據自身顏色以及週遭的圖樣做一個分類，當作這個物體紋理的元素。利用這個猜測出來的紋理特性，我們可以對這個材質做不同光源下的反應模擬以及對不同物體作材質的轉換。
並列摘要
In this thesis, we present a texture synthesis method for realistic rendering without acquiring the actual reflectance properties. The method is based on the observation that many objects have texture repeatedly laid on different locations of their surface. These samples form a pretty sparse set of BTFs. Our goal is to extract the underlying texture from photographs of the object, and to transfer the texture to other objects under different illuminations. This method is very simple and provides pseudo-BTFs reflectance, using texture synthesis approaches. The input data is acquired directly from a few of photographs. These photographs contain appearances of the object with different lighting directions at a fixed viewpoint. We use Photometric Stereo to estimate the normal map and the unshaded image in preprocessing. Then, different texture points (texels) are recognized by their pixel values with neighborhood matching, using segmentation and labeling. Therefore, we can transfer the texture to another object and render it under different illumination conditions using these clustered texels.