3D Face Reconstruction with Silhouette Constraints

نویسندگان

  • Qiyang Hu
  • Matthias Zwicker
  • Paolo Favaro
چکیده

In this paper we introduce silhouette constraints to improve the quality of unconstrained 3D face reconstruction. Previously, state of the art unconstrained 3D face reconstruction techniques relied solely on photometric consistency and matching sparse facial landmarks. We show that constraining the silhouettes of the 3D reconstruction to match silhouettes in the input images can further improve reconstruction quality. Our technique automatically detects silhouettes and iteratively matches silhouette points computed from the current 3D reconstruction with silhouettes in the input images. We demonstrate that our results improve on the previous state of the art in unconstrained 3D face reconstruction and that our additional constraints can easily be included in the iterative reconstruction at little additional cost.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Image Based 3D Face Reconstruction: a Survey

The use of 3D data in face image processing applications has received considerable attention during the last few years. A major issue for the implementation of 3D face processing systems is the accurate and real time acquisition of 3D faces using low cost equipment. In this paper we provide a survey of 3D reconstruction methods used for generating the 3D appearance of a face using either a sing...

متن کامل

Silhouettes Fusion for 3D Shapes Modeling with Ghost Object Removal

In this paper, we investigate a practical framework to compute a 3D shape estimation of multiple objects in real-time from silhouette probability maps in multi-view environments. A popular method called Shape From Silhouette (SFS), computes a 3D shape estimation from binary silhouette masks. This method has several limitations: The acquisition space is limited to the intersection of the camera ...

متن کامل

Silhouette Extraction for Visual Hull Reconstruction

Most of volumetric 3D reconstruction methods need accurate silhouette information of foreground objects for the reliable 3D scene reconstruction of the objects. We present an approach to silhouette extraction based on our change detection method [1] using a statistical model and graph cuts based optimization. We describe some requirements for visual hull reconstruction. We show that our change ...

متن کامل

3D Reconstruction of Simple Objects from A Single View Silhouette Image

While recent deep neural networks have achieved promising results for 3D reconstruction from a single-view image, these rely on the availability of RGB textures in images and extra information as supervision. In this work, we propose novel stacked hierarchical networks and an end to end training strategy to tackle a more challenging task for the first time, 3D reconstruction from a single-view ...

متن کامل

Homography Based Parallel Volume Intersection: Toward Real-Time Volume Reconstruction using Active Cameras

Silhouette volume intersection is one of the most popular ideas for reconstructing the 3D volume of an object from multi-viewpoint silhouette images. This paper presents a novel parallel volume intersection method based on planeto-plane homography for real-time 3D volume reconstruction using active cameras. This paper mainly focuses on the acceleration of back-projection from silhouette images ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016