FaceWarehouse: a 3D Facial Expression Database for Visual Computing

Introduction

FaceWarehouse is a database of 3D facial expressions for visual computing applications. Using a Kinect RGBD camera, we captured 150 individuals aged 7-80 from various ethnic backgrounds. For each person, we captured the RGBD data of her different expressions, including the neutral expression and 19 other expressions such as mouth-opening, smile, kiss, etc. For every RGBD raw data record, a set of facial feature points on the color image such as eye corners, mouth contour and the nose tip are automatically localized, and manually adjusted if better accuracy is required. We then deform a template facial mesh to fit the depth data as closely as possible while matching the feature points on the color image to their corresponding points on the mesh. From these fitted face meshes, we construct a set of individual-specific expression blendshapes for each person.

Obtaining the data

We make all RGBD scans, feature points and the fitted meshes available for academic research purposes. However, as human face is very personal, we only send the data to approved researchers. To obtain a copy, please send an email to kunzhou at acm doc org stating
(1) your name, title, affiliation
(2) your intended use of the data
(3) a statement saying that you accept the following terms of licensing:
The rights to copy, distribute, and use the data (including the RGBD images and 3D models) you are being given access to are under the control of Kun Zhou, head of the Graphics and Parallel Systems Lab, Zhejiang University. You are hereby given permission to copy this data in electronic or hardcopy form for your own scientific use and to distribute it for scientific use to colleagues within your research group. Inclusion of rendered images or video made from this data in a scholarly publication (printed or electronic) is also permitted. In this case, credit must be given to the publication: FaceWarehouse: a 3D Facial Expression Database for Visual Computing. However, the data may not be included in the electronic version of a publication, nor placed on the Internet. These restrictions apply to any representations (other than images or video) derived from the data, including but not limited to simplifications, remeshing, and the fitting of smooth surfaces. The making of physical replicas this data is prohibited, and the data may not be distributed to students in connection with a class. For any other use, including distribution outside your research group, written permission is required from Kun Zhou. Any commercial use of the data is prohibited. Commercial use includes but is not limited to sale of the data, derivatives, replicas, images, or video, inclusion in a product for sale, or inclusion in advertisements (printed or electronic), on commercially-oriented web sites, or in trade shows.

File formats

We store the data for different persons into into different directories. In each directory "Tester_xx", we store the RGBD data, the labelled 74 landmarks, the reconstructed meshes, and user-specific blendshapes for this person.

 

Reference

Cao Chen, Yanlin Weng, Shun Zhou, Yiying Tong, Kun Zhou: "FaceWarehouse: a 3D Facial Expression Database for Visual Computing", IEEE Transactions on Visualization and Computer Graphics, 20(3): 413-425, 2014, [PDF] [Video]

Related Work

Cao Chen, Qiming Hou, Kun Zhou: "Displaced Dynamic Expression Regression for Real-time Facial Tracking and Animation", ACM Transactions on Graphics (SIGGRAPH), 2014. [PDF] [Video]

Cao Chen, Yanlin Weng, Steve Lin, Kun Zhou: "3D Shape Regression for Real-time Facial Animation", ACM Transactions on Graphics (SIGGRAPH), 32(4): 41, 2013, [PDF] [Video]

Yanlin Weng, Cao Chen, Qiming Hou, Kun Zhou: "Real-time Facial Animation on Mobile Devices", Graphical Models, 76(3): 172-179, 2014. [PDF] [Video]