OmniVoxel: A Fast and Precise Reconstruction Method of Omnidirectional Neural Radiance Field

TL;DR

This paper introduces OmniVoxel, a fast and accurate method for reconstructing omnidirectional neural radiance fields using spherical voxelization and feature voxels, significantly reducing training time while maintaining high quality.

Contribution

The paper presents a novel spherical voxelization approach and feature voxel representation to accelerate neural radiance field reconstruction for omnidirectional images.

Findings

Achieves 20-40 minutes per scene reconstruction time.

Outperforms existing methods on synthetic and real datasets.

Maintains high reconstruction quality with complex geometries.

Abstract

This paper proposes a method to reconstruct the neural radiance field with equirectangular omnidirectional images. Implicit neural scene representation with a radiance field can reconstruct the 3D shape of a scene continuously within a limited spatial area. However, training a fully implicit representation on commercial PC hardware requires a lot of time and computing resources (15 $\sim$ 20 hours per scene). Therefore, we propose a method to accelerate this process significantly (20 $\sim$ 40 minutes per scene). Instead of using a fully implicit representation of rays for radiance field reconstruction, we adopt feature voxels that contain density and color features in tensors. Considering omnidirectional equirectangular input and the camera layout, we use spherical voxelization for representation instead of cubic representation. Our voxelization method could balance the reconstruction quality of the inner scene and outer scene. In addition, we adopt the axis-aligned positional encoding method on the color features to increase the total image quality. Our method achieves satisfying empirical performance on synthetic datasets with random camera poses. Moreover, we test our method with real scenes which contain complex geometries and also achieve state-of-the-art performance. Our code and complete dataset will be released at the same time as the paper publication.