合成具細紋之三維臉部表情之研究

Abstract

想要產生一張表情栩栩如生的三維人臉一向都要花費許多人力與時間，即使是經驗豐富的動畫師，仍然要花許多時間在人臉表情的細部調整與修改上。在今日的電影與遊戲製作中，真實表情的動作資料，可藉由三維動態捕捉技術擷取，並且被用來加速三維人臉表情的製作。然而，一般的三維動態捕捉技術僅能擷取較大維度的臉部幾何，對於臉部細微的紋理變化則很難有效捕捉。 在本篇論文中，我們針對臉部細紋的合成與表情的編輯，提出了一個以特徵點驅動的具細紋之三維臉部表情合成系統，此系統可分為兩個主要部分—三維臉部表情的編輯與臉部細微紋理的擷取。我們的系統提供了使用者一個較為直覺的編輯介面，並利用一群指定的臉部特徵點之間的幾何關係，使用一群範例影像估算並合成出新的表情的近似三維幾何結構與相對的法向量或二維外觀影像。除了用在單純的具細紋表情之編輯上，此一技術所產生的臉部細紋資料亦可進一步用在強化現有三維動態捕捉技術所產生的人臉表情上。

Producing a life-like 3D facial expression is usually a labor-intensive process. Even for an experienced animator, it spends much time on trial-and-error procedure. In movie and game industries, motion capture techniques and 3D scanning, acquiring motion data from real persons, are used to speed up the production. However, acquiring dynamic and subtle details, such as wrinkles, on a face are still difficult or expensive. In this thesis, we developed a feature-point-driven approach to synthesize novel expressions with details. Our work can be divided into two main parts: acquisition of 3D facial details and expression synthesis. By employing geometric relation between specific feature points, our system provides an intuitive editing tool to synthesize 3D geometry and corresponding 3D detailed normal or 2D textures of novel expressions. Besides expression editing, the proposed method can also be extended to enhance existing motion capture data with facial details.