FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset
This work addresses the need for high-quality, controllable 3D face models in computer vision and graphics, particularly for East Asian faces, and is incremental as it builds on existing morphable model techniques with a novel coarse-to-fine structure.
The authors tackled the problem of creating a fine-grained and detail-controllable 3D face morphable model by building FaceVerse from a hybrid dataset of 60K RGB-D images and 2K 3D head scans, resulting in a model that outperforms state-of-the-art methods in experiments.
We present FaceVerse, a fine-grained 3D Neural Face Model, which is built from hybrid East Asian face datasets containing 60K fused RGB-D images and 2K high-fidelity 3D head scan models. A novel coarse-to-fine structure is proposed to take better advantage of our hybrid dataset. In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc. Then in the fine module, a conditional StyleGAN architecture trained with high-fidelity scan models is introduced to enrich elaborate facial geometric and texture details. Note that different from previous methods, our base and detailed modules are both changeable, which enables an innovative application of adjusting both the basic attributes and the facial details of 3D face models. Furthermore, we propose a single-image fitting framework based on differentiable rendering. Rich experiments show that our method outperforms the state-of-the-art methods.