Fine-Scale Face Fitting and Texture Fusion With Inverse Renderer

3D face reconstruction from a single image still suffers from low accuracy and inability to recover textures in invisible regions. In this paper, we propose a method for generating a 3D portrait with complete texture. The coarse face-and-head model and texture parameters are obtained using 3D Morphable Model fitting. We design an image-geometric inverse renderer that acquires normal, albedo, and light to jointly reconstruct the facial details. Then, we use a texture fusion network to extract the valid texture from rendered faces employing different viewpoints. Specifically, this fused texture recovers the invisible region of the input face, which illustrates the realistic surface of our 3D geometric model. Our approach faithfully reconstructs the original face details, including the profiles and the head region. Extensive experiments are performed to demonstrate that our method outperforms state-of-the-art techniques in various challenging scenarios.

Introduction

3DAVATAR creation has great theoretical significance and practical value in the fields of computer graphics and virtual reality. We have witnessed great success of high-quality face model generation in the last few years, and this technology plays an important role in entertainment and multimedia communications. However, the 3D avatar creation still suffers from expensive artificial cost and complex equipment for capturing. We aim to generate a complete photorealistic human portrait model from a single “in-the-wild” face image acquired conveniently.