Gaussian activated neural radiance fields for high fidelity reconstruction and pose estimation
SF Chng, S Ramasinghe, J Sherrah… - European Conference on …, 2022 - Springer
European Conference on Computer Vision, 2022•Springer
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 …
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 …
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.
Springer