HarmonicNeRF: Geometry-Informed Synthetic View Augmentation for 3D Scene Reconstruction in Driving Scenarios

TL;DR

HarmonicNeRF enhances 3D scene reconstruction in autonomous driving by augmenting NeRF with geometry-informed synthetic views using spherical harmonics and proxy geometry, leading to improved depth synthesis and scene accuracy.

Contribution

This work introduces HarmonicNeRF, which integrates spherical harmonics and proxy geometry for better scene reconstruction in sparse-view outdoor environments.

Findings

Outperforms existing methods on KITTI, Argoverse, NuScenes datasets.

Achieves state-of-the-art novel depth view synthesis.

Improves scene reconstruction accuracy in autonomous driving scenarios.

Abstract

In the realm of autonomous driving, achieving precise 3D reconstruction of the driving environment is critical for ensuring safety and effective navigation. Neural Radiance Fields (NeRF) have shown promise in creating highly detailed and accurate models of complex environments. However, the application of NeRF in autonomous driving scenarios encounters several challenges, primarily due to the sparsity of viewpoints inherent in camera trajectories and the constraints on data collection in unbounded outdoor scenes, which typically occur along predetermined paths. This limitation not only reduces the available scene information but also poses significant challenges for NeRF training, as the sparse and path-distributed observational data leads to under-representation of the scene's geometry. In this paper, we introduce HarmonicNeRF, a novel approach for outdoor self-supervised monocular scene reconstruction. HarmonicNeRF capitalizes on the strengths of NeRF and enhances surface reconstruction accuracy by augmenting the input space with geometry-informed synthetic views. This is achieved through the application of spherical harmonics to generate novel radiance values, taking into careful consideration the color observations from the limited available real-world views. Additionally, our method incorporates proxy geometry to effectively manage occlusion, generating radiance pseudo-labels that circumvent the limitations of traditional image-warping techniques, which often fail in sparse data conditions typical of autonomous driving environments. Extensive experiments conducted on the KITTI, Argoverse, and NuScenes datasets demonstrate our approach establishes new benchmarks in synthesizing novel depth views and reconstructing scenes, significantly outperforming existing methods. Project page: https://github.com/Jiawei-Yao0812/HarmonicNeRF