MapNeRF: Incorporating Map Priors into Neural Radiance Fields for Driving View Simulation

TL;DR

MapNeRF enhances neural radiance fields with map priors to improve out-of-trajectory view synthesis in autonomous driving, ensuring semantic road consistency and multi-view accuracy.

Contribution

This work introduces a novel method to incorporate map priors into neural radiance fields, enabling better extrapolated view synthesis with semantic consistency.

Findings

Produces semantically consistent out-of-trajectory views

Improves multi-view accuracy in driving simulations

Demonstrates effectiveness through experimental results

Abstract

Simulating camera sensors is a crucial task in autonomous driving. Although neural radiance fields are exceptional at synthesizing photorealistic views in driving simulations, they still fail to generate extrapolated views. This paper proposes to incorporate map priors into neural radiance fields to synthesize out-of-trajectory driving views with semantic road consistency. The key insight is that map information can be utilized as a prior to guiding the training of the radiance fields with uncertainty. Specifically, we utilize the coarse ground surface as uncertain information to supervise the density field and warp depth with uncertainty from unknown camera poses to ensure multi-view consistency. Experimental results demonstrate that our approach can produce semantic consistency in deviated views for vehicle camera simulation. The supplementary video can be viewed at https://youtu.be/jEQWr-Rfh3A.