RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation

TL;DR

This paper introduces a simple yet efficient method, RoMe, for large-scale Road surface reconstruction via Mesh representations, which can properly preserve road surface details, with only linear computational complexity to road areas.

Abstract

In autonomous driving applications, accurate and efficient road surface reconstruction is paramount. This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces. Leveraging a unique mesh representation, RoMe ensures that the reconstructed road surfaces are accurate and seamlessly aligned with semantics. To address challenges in computational efficiency, we propose a waypoint sampling strategy, enabling RoMe to reconstruct vast environments by focusing on sub-areas and subsequently merging them. Furthermore, we incorporate an extrinsic optimization module to enhance the robustness against inaccuracies in extrinsic calibration. Our extensive evaluations of both public datasets and wild data underscore RoMe's superiority in terms of speed, accuracy, and robustness. For instance, it costs only 2 GPU hours to recover a road surface of 600*600 square meters from thousands of images. Notably, RoMe's capability extends beyond mere reconstruction, offering significant value for autolabeling tasks in autonomous driving applications. All related data and code are available at https://github.com/DRosemei/RoMe.

Figures (19)

• Figure 1: Road surface reconstruction results (KITTI odometry sequence-00) using our proposed RoMe, covering an area of approximately $600\times600$ square meters. The first row displays the input image sequence with semantic annotations. The second row showcases the final results with close-up details highlighted in red rectangles: the reconstructed BEV RGB surface and its corresponding BEV semantics.
• Figure 2: Overview of RoMe. (a) Waypoint sampling: The green line depicts the camera's path. Red and blue boxes indicate neighboring subareas, with corresponding red and blue dots representing waypoint samples, aiding in faster training. (b) Mesh initialization: Upon initializing mesh $M$, vertices are assigned a position $(x, y, z)$, color $(r, g, b)$, and semantic attributes. The elevation $z$ of each vertex is fine-tuned using an elevation MLP network. (c) Optimization: The optimization targets, $L_{color}$ and $L_{sem}$, enable rendering mesh $M$ into RGB images with associated semantics. The parameters ($z$, $(r, g, b)$, and Sem., highlighted in blue in (b)) are collectively adjusted to produce the final road mesh $M$. Best viewed in color.
• Figure 3: Street reconstruction by StreetSurf guo2023streetsurf and RoMe.
• Figure 4: Illustration of waypoint sampling. The camera trajectory is represented by the green line. Distinct colored dots and their associated boxes indicate sampled waypoints and their corresponding sub-areas across various epochs.
• Figure 5: Epochs and losses in our preliminary experiments.