ToonTalker: Cross-Domain Face Reenactment

Yuan Gong, Yong Zhang, Xiaodong Cun, Fei Yin, Yanbo Fan, Xuan Wang, Baoyuan Wu, Yujiu Yang

• We propose a novel method for cross-domain reenactment without paired data.

NOFA: NeRF-based One-shot Facial Avatar Reconstruction

Wangbo Yu, Yanbo Fan$^\dagger$, Yong Zhang$^\dagger$, Xuan Wang$^\dagger$, Fei Yin, Yunpeng Bai, Yan-Pei Cao, Ying Shan, Yang Wu, Zhongqian Sun, Baoyuan Wu

• We propose a one-shot 3D facial avatar reconstruction framework, which only requires a single source image to reconstruct high-fidelity 3D facial avatar, by leveraging the rich generative prior of 3D GAN and developing an efficient encoder-decoder network.

Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

Jingxiang Sun, Xuan Wang, Lizhen Wang, Xiaoyu Li, Yong Zhang, Hongwen Zhang, Yebin Liu

Project |

• We propose a 3D representation called Generative Texture-Rasterized Tri-planes that learns Generative Neural Textures on top of parametric mesh templates and then projects them into three orthogonal-viewed feature planes through rasterization, forming a tri-plane feature representation for volume rendering.

UV Volumes for Real-time Rendering of Editable Free-view Human Performance

Yue Chen$^\star$, Xuan Wang$^\star$, Xingyu Chen, Qi Zhang, Xiaoyu Li, Yu Guo, Jue Wang, Fei Wang

Project |

• We propose the UV Volumes, a new approach that can render an editable free-view video of a human performer in real-time.

L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields

Yue Chen$^\star$, Xingyu Chen$^\star$, Xuan Wang$^\dagger$, Qi Zhang, Yu Guo$^\dagger$, Ying Shan, Fei Wang

Project |

• We propose L2G-NeRF, a Local-to-Global registration method for bundle-adjusting Neural Radiance Fields: first, a pixel-wise flexible alignment, followed by a framewise constrained parametric alignment.

High-fidelity Facial Avatar Reconstruction from Monocular Video with Generative Priors

Yunpeng Bai, Yanbo Fan, Xuan Wang, Yong Zhang, Jingxiang Sun, Chun Yuan, Ying Shan

• We propose a new method for NeRF-based facial avatar reconstruction that utilizes 3D-aware generative prior. Different from existing works that depend on a conditional deformation field for dynamic modeling, we propose to learn a personalized generative prior, which is formulated as a local and low dimensional subspace in the latent space of 3D-GAN.

SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Wenxuan Zhang, Xiaodong Cun, Xuan Wang, Yong Zhang, Xi Shen, Yu Guo, Ying Shan, Fei Wang

Project | 🔥

• We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.

3D GAN Inversion with Facial Symmetry Prior

Fei Yin, Yong Zhang, Xuan Wang, Tengfei Wang, Xiaoyu Li, Yuan Gong, Yanbo Fan, Xiaodong Cun, Ying Shan, Cengiz Oztireli, Yujiu Yang

Project |

• We propose a novel method to promote 3D GAN inversion by introducing facial symmetry prior.

Local Implicit Ray Function for Generalizable Radiance Field Representation

Xin Huang, Qi Zhang, Ying Feng, Xiaoyu Li, Xuan Wang, Qing Wang

Project |

• For generalisable neural radiance fileds, we propose LIRF to aggregate the information from conical frustums to construct a ray.

High-Fidelity Clothed Avatar Reconstruction from a Single Image

Tingting Liao, Xiaomei Zhang, Yuliang Xiu, Hongwei Yi, Xudong Liu, Guo-Jun Qi, Yong Zhang, Xuan Wang, Xiangyu Zhu, Zhen Lei

Project

• By combining the advantages of the high accuracy of optimization-based methods and the efficiency of learning-based methods, we propose a coarse-tofine way to realize a high-fidelity clothed avatar reconstruction (CAR) from a single image.

IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis

Jingxiang Sun, Xuan Wang, Yichun Shi, Lizhen Wang, Jue Wang, Yebin Liu

Project |

• We propose the IDE-3D, a locally disentangled, semantics-aware 3D face generator which supports interactive 3D face synthesis and local editing. Our method supports various free-view portrait editing tasks with the state-of-the-art performance in photorealism and efficiency.

Neural Parameterization for Dynamic Human Head Editing

Li Ma, Xiaoyu Li, Jing Liao, Xuan Wang, Qi Zhang, Jue Wang, Pedro Sander

Project |

• Neural Parameterization (NeP), a hybrid representation that provides the advantages of both implicit and explicit methods.

VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Kun Cheng, Xiaodong Cun, Yong Zhang, Menghan Xia, Fei Yin, Mingrui Zhu, Xuan Wang, Jue Wang, Nannan Wang

Project | 🔥

• VideoReTalking, a new system to edit the faces of a real-world talking head video according to an input audio, producing a high-quality and lip-syncing output video even with a different emotion.

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang

Project |

• We propose a novel unified framework based on a pre-trained StyleGAN that enables a set of powerful functionalities, i.e., high-resolution video generation, disentangled control by driving video or audio, and flexible face editing.

FENeRF: Face Editing in Neural Radiance Fields

Jingxiang Sun, Xuan Wang$^\dagger$, Yong Zhang, Xiaoyu Li, Qi Zhang, Yebin Liu, Jue Wang

Project |

• The first portrait image generator that is locally editable and strictly view-consistent.

HDR-NeRF: High Dynamic Range Neural Radiance Fields

Xin Huang, Qi Zhang, Ying Feng, Hongdong Li, Xuan Wang, Qing Wang

Project |

• High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures.

Hallucinated Neural Radiance Fields in the Wild

Xingyu Chen, Qi Zhang, Xiaoyu Li, Yue Chen, Feng Ying, Xuan Wang, Jue Wang

Project |

• An appearance hallucination module to handle time-varying appearances and transfer them to novel views.

Deblur-NeRF: Neural Radiance Fields from Blurry Images

Li Ma, Xiaoyu Li, Jing Liao, Qi Zhang, Xuan Wang, Jue Wang, Pedro V Sander

Project |

• The first method that can recover a sharp NeRF from blurry input.

On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos

Zhi Li$^\star$, Xuan Wang$^\star$, Fei Wang, Peilin Jiang

• The method that exploits monocular videos to complement the training dataset for the singleimage 3D human pose estimation tasks.

Template-free 3D Reconstruction of Poorly-textured Nonrigid Surfaces

Xuan Wang, Mathieu Salzmann, Fei Wang, Jizhong Zhao

Project

• A template-free approach to reconstructing a poorly-textured, deformable surface.