ML Anthology

Multi-View Neural Human Rendering

Minye Wu, Yuehao Wang, Qiang Hu, Jingyi Yu
CVPR 2020
doi:10.1109/CVPR42600.2020.00175 /cvpr/2020/wu2020cvpr-multiview/

Abstract

We present an end-to-end Neural Human Renderer (NHR) for dynamic human captures under the multi-view setting. NHR adopts PointNet++ for feature extraction (FE) to enable robust 3D correspondence matching on low quality, dynamic 3D reconstructions. To render new views, we map 3D features onto the target camera as a 2D feature map and employ an anti-aliased CNN to handle holes and noises. Newly synthesized views from NHR can be further used to construct visual hulls to handle textureless and/or dark regions such as black clothing. Comprehensive experiments show NHR significantly outperforms the state-of-the-art neural and image-based rendering techniques, especially on hands, hair, nose, foot, etc.

PDF CVPR Semantic Scholar

Cite

Text

Wu et al. "Multi-View Neural Human Rendering." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020. doi:10.1109/CVPR42600.2020.00175

Markdown

[Wu et al. "Multi-View Neural Human Rendering." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.](https://mlanthology.org/cvpr/2020/wu2020cvpr-multiview/) doi:10.1109/CVPR42600.2020.00175

BibTeX

@inproceedings{wu2020cvpr-multiview,
  title     = {{Multi-View Neural Human Rendering}},
  author    = {Wu, Minye and Wang, Yuehao and Hu, Qiang and Yu, Jingyi},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2020},
  doi       = {10.1109/CVPR42600.2020.00175},
  url       = {https://mlanthology.org/cvpr/2020/wu2020cvpr-multiview/}
}