paper-with-me

홈 › Papers

Reconstructing Personalized Semantic Facial NeRF Models From Monocular Video

2022-10-12 · Xuan Gao, Chenglai Zhong, Jun Xiang, Yang Hong, Yudong Guo, Juyong Zhang

We present a novel semantic model for human head defined with neural radiance field. The 3D-consistent head model consist of a set of disentangled and interpretable bases, and can be driven by low-dimensional expression coefficients. Thanks to the powerful representation ability of neural radiance field, the constructed model can represent complex facial attributes including hair, wearings, which can not be represented by traditional mesh blendshape. To construct the personalized semantic facial model, we propose to define the bases as several multi-level voxel fields. With a short monocular RGB video as input, our method can construct the subject's semantic facial NeRF model with only ten to twenty minutes, and can render a photo-realistic human head image in tens of miliseconds with a given expression coefficient and view direction. With this novel representation, we apply it to many tasks like facial retargeting and expression editing. Experimental results demonstrate its strong representation ability and training/inference speed. Demo videos and released code are provided in our project page: https://ustc3dv.github.io/NeRFBlendShape/

📄 PDF Abstract BibTeX arXiv:2210.06108

Code (1)

USTC3DV/NeRFBlendShape-code 공식 구현 pytorch

Tasks

NeRF

Similar Papers 제목 키워드 기반

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

2022-11-28 · CVPR 2023 1 · Yunpeng Bai, Yanbo Fan, Xuan Wang, Yong Zhang 외

High-fidelity facial avatar reconstruction from a monocular video is a significant research problem in computer graphics and computer vision. Recently, Neural Radiance Field (NeRF) has shown impressive novel view renderi…

Face ReenactmentNeRFNovel View SynthesisVocal Bursts Intensity Prediction

MI-NeRF: Learning a Single Face NeRF from Multiple Identities

2024-03-29 · Aggelina Chatziagapi, Grigorios G. Chrysos, Dimitris Samaras

In this work, we introduce a method that learns a single dynamic neural radiance field (NeRF) from monocular talking face videos of multiple identities. NeRFs have shown remarkable results in modeling the 4D dynamics and…

NeRF

Refined Geometry-guided Head Avatar Reconstruction from Monocular RGB Video

2025-03-27 · Pilseo Park, Ze Zhang, Michel Sarkis, Ning Bi 외

High-fidelity reconstruction of head avatars from monocular videos is highly desirable for virtual human applications, but it remains a challenge in the fields of computer graphics and computer vision. In this paper, we …

NeRF

PAV: Personalized Head Avatar from Unstructured Video Collection

2024-07-22 · Akin Caliskan, Berkay Kicanaoglu, Hyeongwoo Kim

We propose PAV, Personalized Head Avatar for the synthesis of human faces under arbitrary viewpoints and facial expressions. PAV introduces a method that learns a dynamic deformable neural radiance field (NeRF), in parti…

NeRF

Talk3D: High-Fidelity Talking Portrait Synthesis via Personalized 3D Generative Prior

2024-03-29 · Jaehoon Ko, Kyusun Cho, Joungbin Lee, Heeji Yoon 외

Recent methods for audio-driven talking head synthesis often optimize neural radiance fields (NeRF) on a monocular talking portrait video, leveraging its capability to render high-fidelity and 3D-consistent novel-view fr…

NeRF