Novel View Synthesis for High-fidelity Headshot Scenes
This work addresses a practical need for high-fidelity face rendering in applications like virtual reality or entertainment, though it is incremental as it builds on established techniques like NeRF and 3DMM.
The paper tackles the problem of synthesizing novel views of scenes with human faces while preserving fine skin details like moles and pores, which existing methods like NeRF fail to maintain. It proposes a hybrid method combining NeRF and 3DMM with a GAN, resulting in photorealistic outputs as demonstrated in experiments on real-world scenes.
Rendering scenes with a high-quality human face from arbitrary viewpoints is a practical and useful technique for many real-world applications. Recently, Neural Radiance Fields (NeRF), a rendering technique that uses neural networks to approximate classical ray tracing, have been considered as one of the promising approaches for synthesizing novel views from a sparse set of images. We find that NeRF can render new views while maintaining geometric consistency, but it does not properly maintain skin details, such as moles and pores. These details are important particularly for faces because when we look at an image of a face, we are much more sensitive to details than when we look at other objects. On the other hand, 3D Morpable Models (3DMMs) based on traditional meshes and textures can perform well in terms of skin detail despite that it has less precise geometry and cannot cover the head and the entire scene with background. Based on these observations, we propose a method to use both NeRF and 3DMM to synthesize a high-fidelity novel view of a scene with a face. Our method learns a Generative Adversarial Network (GAN) to mix a NeRF-synthesized image and a 3DMM-rendered image and produces a photorealistic scene with a face preserving the skin details. Experiments with various real-world scenes demonstrate the effectiveness of our approach. The code will be available on https://github.com/showlab/headshot .