Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation

Shin-Fang Chng; Sameera Ramasinghe; Jamie Sherrah; Simon Lucey

ECCV 2022poster133 citations

Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation

Shin-Fang Chng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey

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."

BibTeX

@inproceedings{eccv2022_gaussianactivate,
  title = {Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation},
  author = {Shin-Fang Chng and Sameera Ramasinghe and Jamie Sherrah and Simon Lucey},
  booktitle = {ECCV 2022},
  year = {2022}
}