NeRO: Neural Road Surface Reconstruction
This work addresses road surface reconstruction for autonomous driving applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles road surface reconstruction for autonomous driving by introducing a position encoding MLP framework that takes world coordinates as input and outputs height, color, and semantic information. The method demonstrates effectiveness through compatibility with various data sources (e.g., LiDAR, camera poses), robustness to semantic noise, and fast training speed.
Accurately reconstructing road surfaces is pivotal for various applications especially in autonomous driving. This paper introduces a position encoding Multi-Layer Perceptrons (MLPs) framework to reconstruct road surfaces, with input as world coordinates x and y, and output as height, color, and semantic information. The effectiveness of this method is demonstrated through its compatibility with a variety of road height sources like vehicle camera poses, LiDAR point clouds, and SFM point clouds, robust to the semantic noise of images like sparse labels and noise semantic prediction, and fast training speed, which indicates a promising application for rendering road surfaces with semantics, particularly in applications demanding visualization of road surface, 4D labeling, and semantic groupings.