Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation
Abstract
Despite Neural Radiance Fields (NeRF) showing compelling results in photorealistic novel views synthesis of real-world scenes, most existing approaches require accurate prior camera poses. Although approaches for jointly recovering the radiance field and camera pose exist, they rely on a cumbersome coarse-to-fine auxiliary positional embedding to ensure good performance. We present Gaussian Activated Neural Radiance Fields (GARF), a new positional embedding-free neural radiance field architecture -- employing Gaussian activations -- that is competitive with the current state-of-the-art in terms of high fidelity reconstruction and pose estimation.
Cite
Text
Chng et al. "Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19827-4_16Markdown
[Chng et al. "Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/chng2022eccv-gaussian/) doi:10.1007/978-3-031-19827-4_16BibTeX
@inproceedings{chng2022eccv-gaussian,
title = {{Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation}},
author = {Chng, Shin-Fang and Ramasinghe, Sameera and Sherrah, Jamie and Lucey, Simon},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19827-4_16},
url = {https://mlanthology.org/eccv/2022/chng2022eccv-gaussian/}
}