Timezone: »

 
Poster
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Keqiang Sun · Shangzhe Wu · Zhaoyang Huang · Ning Zhang · Quan Wang · Hongsheng Li

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #240

Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of controllability, e.g., controlling the shapes, expressions, textures, and poses of the generated face images. However, these methods focus on 2D image generative models, which are prone to producing inconsistent face images under large expression and pose changes. In this paper, we propose a new NeRF-based conditional 3D face synthesis framework, which enables 3D controllability over the generated face images by imposing explicit 3D conditions from 3D face priors. At its core is a conditional Generative Occupancy Field (cGOF) that effectively enforces the shape of the generated face to commit to a given 3D Morphable Model (3DMM) mesh. To achieve accurate control over fine-grained 3D face shapes of the synthesized image, we additionally incorporate a 3D landmark loss as well as a volume warping loss into our synthesis algorithm. Experiments validate the effectiveness of the proposed method, which is able to generate high-fidelity face images and shows more precise 3D controllability than state-of-the-art 2D-based controllable face synthesis methods.

Author Information

Keqiang Sun (Chinese University of Hong Kong)
Shangzhe Wu (University of Oxford)
Zhaoyang Huang (The Chinese University of Hong Kong)
Ning Zhang (Sensetime)
Quan Wang (SenseTime Group Limited, SenseTime Group Limited)
Hongsheng Li (The Chinese University of Hong Kong)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors