Portrait Neural Radiance Fields from a Single Image
@article{Gao2020PortraitNR, title={Portrait Neural Radiance Fields from a Single Image}, author={Chen Gao and YiChang Shih and Wei-Sheng Lai and Chia-Kai Liang and J. Huang}, journal={ArXiv}, year={2020}, volume={abs/2012.05903} }
We present a method for estimating Neural Radiance Fields (NeRF) from a single headshot portrait. While NeRF has demonstrated high-quality view synthesis, it requires multiple images of static scenes and thus impractical for casual captures and moving subjects. In this work, we propose to pretrain the weights of a multilayer perceptron (MLP), which implicitly models the volumetric density and colors, with a meta-learning framework using a light stage portrait dataset. To improve the… CONTINUE READING
Figures and Tables from this paper
2 Citations
References
SHOWING 1-10 OF 70 REFERENCES
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
- Computer Science
- ArXiv
- 2020
- 26
- PDF
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- Computer Science
- ECCV
- 2020
- 130
- Highly Influential
- PDF
Learning Perspective Undistortion of Portraits
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 6
- Highly Influential
- PDF
Deep 3D Portrait From a Single Image
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 6
- Highly Influential
- PDF
Unsupervised Training for 3D Morphable Model Regression
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 121
- PDF
Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 28
- PDF
HoloGAN: Unsupervised Learning of 3D Representations From Natural Images
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 105
- PDF