S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation

TL;DR

S-NeRF++ is a neural reconstruction-based simulation system that generates realistic, manipulable street scenes and vehicles for autonomous driving, improving data diversity and supporting downstream perception tasks.

Contribution

We introduce S-NeRF++, an advanced neural radiance field system that enhances scene synthesis, manipulation, and realism for autonomous driving simulation.

Findings

Generated high-quality, realistic street scenes and vehicles.

Improved perception performance on autonomous driving tasks.

Effectively utilizes noisy LiDAR data for reconstruction.

Abstract

Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, traditional simulation systems, which often heavily rely on manual modeling and 2D image editing, struggled with scaling to extensive scenes and generating realistic simulation data. In this study, we present S-NeRF++, an innovative autonomous driving simulation system based on neural reconstruction. Trained on widely-used self-driving datasets such as nuScenes and Waymo, S-NeRF++ can generate a large number of realistic street scenes and foreground objects with high rendering quality as well as offering considerable flexibility in manipulation and simulation. Specifically, S-NeRF++ is an enhanced neural radiance field for synthesizing large-scale scenes and moving vehicles, with improved scene parameterization and camera pose learning. The system effectively utilizes noisy and sparse LiDAR data to refine training and address depth outliers, ensuring high-quality reconstruction and novel-view rendering. It also provides a diverse foreground asset bank by reconstructing and generating different foreground vehicles to support comprehensive scenario creation.Moreover, we have developed an advanced foreground-background fusion pipeline that skillfully integrates illumination and shadow effects, further enhancing the realism of our simulations. With the high-quality simulated data provided by our S-NeRF++, we found the perception methods enjoy performance boosts on several autonomous driving downstream tasks, further demonstrating our proposed simulator's effectiveness.