OmniVoxel: A Fast and Precise Reconstruction Method of Omnidirectional Neural Radiance Field
This work addresses the computational bottleneck in 3D scene reconstruction for applications like virtual reality and robotics, offering a significant speed-up with competitive quality, though it is incremental as it builds on existing NeRF methods.
The paper tackles the slow training time of neural radiance fields (NeRF) on commercial hardware by proposing OmniVoxel, a method that uses spherical voxelization and feature tensors to reconstruct scenes from omnidirectional images, reducing training time from 15-20 hours to 20-40 minutes per scene while achieving state-of-the-art performance on synthetic and real datasets.
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.