FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction
This work addresses the need for high-quality, expression-specific 3D face modeling in computer vision and graphics, offering a significant dataset and method for research.
The authors tackled the problem of generating detailed 3D face models from single images by introducing FaceScape, a large-scale dataset with 18,760 textured 3D faces from 938 subjects and 20 expressions, and a novel algorithm that predicts riggable 3D models with pore-level geometry.
In this paper, we present a large-scale detailed 3D face dataset, FaceScape, and propose a novel algorithm that is able to predict elaborate riggable 3D face models from a single image input. FaceScape dataset provides 18,760 textured 3D faces, captured from 938 subjects and each with 20 specific expressions. The 3D models contain the pore-level facial geometry that is also processed to be topologically uniformed. These fine 3D facial models can be represented as a 3D morphable model for rough shapes and displacement maps for detailed geometry. Taking advantage of the large-scale and high-accuracy dataset, a novel algorithm is further proposed to learn the expression-specific dynamic details using a deep neural network. The learned relationship serves as the foundation of our 3D face prediction system from a single image input. Different than the previous methods, our predicted 3D models are riggable with highly detailed geometry under different expressions. The unprecedented dataset and code will be released to public for research purpose.