Z Wang, Q She, TE Ward - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably their most significant impact has been in the area of computer vision where …
We introduce GaussianAvatars a new method to create photorealistic head avatars that are fully controllable in terms of expression pose and viewpoint. The core idea is a dynamic 3D …
Y Hong, B Peng, H Xiao, L Liu… - Proceedings of the …, 2022 - openaccess.thecvf.com
In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that integrates the neural radiance field to the parametric representation of the human head. It …
Y Deng, J Yang, J Xiang… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract 3D-aware image generative modeling aims to generate 3D-consistent images with explicitly controllable camera poses. Recent works have shown promising results by training …
The ability to create realistic animatable and relightable head avatars from casual video sequences would open up wide ranging applications in communication and entertainment …
Traditional 3D morphable face models (3DMMs) provide fine-grained control over expression but cannot easily capture geometric and appearance details. Neural volumetric …
Y Xu, B Chen, Z Li, H Zhang, L Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Creating high-fidelity 3D head avatars has always been a research hotspot but there remains a great challenge under lightweight sparse view setups. In this paper we propose …
As 3D facial avatars become more widely used for communication, it is critical that they faithfully convey emotion. Unfortunately, the best recent methods that regress parametric 3D …
While current monocular 3D face reconstruction methods can recover fine geometric details, they suffer several limitations. Some methods produce faces that cannot be realistically …