GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields
CVPR 2024, 2024
A generalizable neural radiance field that efficiently learns human-specific features from sparse observations, enabling real-time novel view synthesis without per-scene optimization, presented at CVPR 2024.
Abstract
We present GHNeRF, a method for learning generalizable human features with efficient neural radiance fields. Our approach enables high-quality human reconstruction and novel view synthesis while maintaining computational efficiency.
Recommended citation:
@inproceedings{dey2024ghnerf,
title={GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields},
author={Dey, Arnab and others},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2024}
}Citation
Dey, Arnab, et al. "GHNeRF: Learning Generalizable Human Features with Efficient Neural Radiance Fields." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2024.