3D-Aware Face Editing via Warping-Guided Latent Direction Learning

3D facial editing, a longstanding task in computer vision with broad applications, is expected to fast and intuitively manipulate any face from arbitrary viewpoints following the user's will. Existing works have limitations in terms of intuitiveness, generalization, and efficiency. To overcome these challenges, we propose FaceEdit3D, which allows users to directly manipulate 3D points to edit a 3D face, achieving natural and rapid face editing. After one or several points are manipulated by users, we propose the tri-plane warping to directly deform the view-independent 3D representation. To address the problem of distortion caused by tri-plane warping, we train a warp-aware encoder to project the warped face onto a standardized latent space. In this space, we further propose directional latent editing to mitigate the identity bias caused by the encoder and realize the disentangled editing of various attributes. Extensive experiments show that our method achieves superior results with rich facial details and nice identity preservation. Our approach also supports general applications like multi-attribute continuous editing and cat/car editing. The project website is https://cyh-sj.github.io/FaceEdit3DI.

1. Introduction

High-quality face editing has long been an important re-search topic in computer vision with a wide range of applications, including social media and film production. Pre-vious methods [16], [36], [43] based on 2D GANs [22], [23] have demonstrated the capability of editing facial images with high-fidelity. Recently, benefiting from the impressive achievements of 3D-aware generative models, especially in generative digital human [2–4, 11, 15, 32, 33, 41, 45, 51, 53, 55, 56, 64], the field of 3D facial editing has further at-tracted significant interest due to its promising capacity of manipulating a 3D representation.