ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction
ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction
This research presents ReSMap, a redundancy-aware framework that fuses camera and satellite data to construct high-definition maps robustly even when onboard cameras fail. By using a Predict-then-Fuse module with per-pixel reliability weights and an Object-Centric Cooperative Multi-modal Query decoder, the system leverages offline-cached satellite images as a complementary source. The model achieves state-of-the-art performance on the nuScenes benchmark across all splits and range settings, setting new records specifically under camera-failure scenarios, demonstrating that satellite imagery serves as practical redundancy for robust online HD mapping.
The paper introduces ReSMap, a camera-satellite fusion framework that uses satellite imagery as redundancy for online HD map construction to maintain robustness during camera failures, achieving state-of-the-art performance on the nuScenes benchmark across all splits and specifically under simulated camera-failure conditions.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Dataset details reported by the source
- Modalities
- camera and satellite BEV features Open source S3
- Tasks
- online HD map construction Open source S1
- Embodiments
- redundancy-aware camera-satellite fusion framework Open source S3
- paper: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
inal conditions, without explicitly addressing them as redundancy when a sensor degrades. To address this gap, we propose ReSMap, a redundancy-aware camera-satellite fusion framework for robust online HD map construction. Our framework explicitly leverages satellite images as a complementary source to improve robustness against camera failures. A Predict-then-Fuse (PTF) module fuses camera and satellite BEV features
Open source S3
ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction
Open source S1
arXiv:2611.04352v1 Announce Type: cross Abstract: Despite recent advances in camera-based online HD map construction, these systems remain susceptible to sensor failures due to their reliance on onboard cameras. In contrast, satellite images remain available independently of real-time sensing conditions as they are cached offline. Existing methods utilizing satellite images, however, primarily leverage them under nom
Open source S2
by using each branch's own prediction confidence as a per-pixel reliability weight, with no learned router. An Object-Centric Cooperative Multi-modal Query (OCMQ) decoder then extends this per-modality separation to the query level: each modality cross-attends only to its own BEV, and per-modality updates are merged through a learned per-token gate. Our model achieves state-of-the-art performance on nuScenes across a
Open source S4
ll splits and range settings. More importantly, it also sets the new state-of-the-art under camera-failure scenarios, demonstrating that satellite images serve not only as a strong prior but as practical redundancy for robust online HD mapping.
Open source S5
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org