Recently, the centerline has become a popular representation of lanes due to its advantages in solving the road topology problem. To enhance centerline prediction, we have developed a new approach called TopoMask. Unlike previous methods that rely on keypoints or parametric methods, TopoMask utilizes an instance-mask-based formulation coupled with a masked-attention-based transformer architecture. We introduce a quad-direction label representation to enrich the mask instances with flow information and design a corresponding post-processing technique for mask-to-centerline conversion. Additionally, we demonstrate that the instance-mask formulation provides complementary information to parametric Bezier regressions, and fusing both outputs leads to improved detection and topology performance. Moreover, we analyze the shortcomings of the pillar assumption in the Lift Splat technique and adapt a multi-height bin configuration. Experimental results show that TopoMask achieves state-of-the-art performance in the OpenLane-V2 dataset, increasing from 44.1 to 49.4 for Subset-A and 44.7 to 51.8 for Subset-B in the V1.1 OLS baseline.
@article{arxiv.2409.11325,
title = {TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problem},
author = {M. Esat Kalfaoglu and Halil Ibrahim Ozturk and Ozsel Kilinc and Alptekin Temizel},
journal= {arXiv preprint arXiv:2409.11325},
year = {2024}
}
Comments
Accepted to ECCV 2024 2nd Workshop on Vision-Centric Autonomous Driving (VCAD). TopoMaskV2 includes significant architectural improvements and extensive ablation studies over the original TopoMask, which received an innovation award in the OpenLane Topology Challenge 2023