IC-Mapper: Instance-Centric Spatio-Temporal Modeling for Online Vectorized Map Construction
This work improves map-building efficiency for autonomous driving systems by enabling real-time, scalable map construction without manual annotation, though it appears incremental as it builds on existing online mapping frameworks.
The paper tackles the problem of online vectorized map construction from visual data by addressing spatial scalability, proposing IC-Mapper with instance-centric temporal association and spatial fusion modules, and demonstrates superiority over state-of-the-art methods on the nuScenes dataset.
Online vector map construction based on visual data can bypass the processes of data collection, post-processing, and manual annotation required by traditional map construction, which significantly enhances map-building efficiency. However, existing work treats the online mapping task as a local range perception task, overlooking the spatial scalability required for map construction. We propose IC-Mapper, an instance-centric online mapping framework, which comprises two primary components: 1) Instance-centric temporal association module: For the detection queries of adjacent frames, we measure them in both feature and geometric dimensions to obtain the matching correspondence between instances across frames. 2) Instance-centric spatial fusion module: We perform point sampling on the historical global map from a spatial dimension and integrate it with the detection results of instances corresponding to the current frame to achieve real-time expansion and update of the map. Based on the nuScenes dataset, we evaluate our approach on detection, tracking, and global mapping metrics. Experimental results demonstrate the superiority of IC-Mapper against other state-of-the-art methods. Code will be released on https://github.com/Brickzhuantou/IC-Mapper.