CVApr 12, 2022

GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation

arXiv:2204.05735v1105 citationsh-index: 57
Originality Incremental advance
AI Analysis

This addresses the need for more efficient and accurate pose estimation in 3D scene reconstruction, though it appears incremental as it builds on existing joint recovery approaches like BARF.

The paper tackles the problem of jointly recovering neural radiance fields and camera poses without accurate prior poses, presenting GARF, which outperforms state-of-the-art methods in high-fidelity reconstruction and pose estimation.

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 (BARF), 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 outperforms the current state-of-the-art in terms of high fidelity reconstruction and pose estimation.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes