vrn：基於直接體積回歸的單幅圖像大姿態三維人臉重建

3D面部重建是一個非常困難的基本計算機視覺問題。目前的系統通常假設多個面部圖像（有時來自同一主題）作為輸入的可用性，並且必須解決許多方法學挑戰，例如在大的面部姿勢，表情和不均勻照明之間建立密集的對應。一般來說，這些方法需要複雜和低效的管道來建模和擬合。在這項工作中，我們提出通過在由2D圖像和3D面部模型或掃描組成的適當數據集上訓練卷積神經網路（CNN）來解決許多這些限制。我們的CNN只使用一個2D面部圖像，不需要精確的對準，也不會形成圖像之間的密集對應，適用於任意麵部姿勢和表情，並可用於重建整個3D面部幾何（包括不可見部分（在訓練期間）和擬合（測試期間）3D變形模型。我們通過一個簡單的CNN架構來實現這一點，該架構對單個2D圖像的3D面部幾何體的體積表示進行直接回歸。我們還展示了如何將面部地標定位的相關任務納入擬議的框架，並有助於提高重建質量，特別是對於大姿勢和面部表情的情況。

3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of methodological challenges such as establishing dense correspondences across large facial poses, expressions, and non-uniform illumination. In general these methods require complex and inefficient pipelines for model building and fitting. In this work, we propose to address many of these limitations by training a Convolutional Neural Network (CNN) on an appropriate dataset consisting of 2D images and 3D facial models or scans. Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model. We achieve this via a simple CNN architecture that performs direct regression of a volumetric representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related task of facial landmark localization can be incorporated into the proposed framework and help improve reconstruction quality, especially for the cases of large poses and facial expressions.

項目地址：https://github.com/AaronJackson/vrn

更多人工智慧教程：http://www.buluo360.com

推薦閱讀：