Hugging Face Papers ↗ · 2026-11-18
Accord: Universal Online Metric Localization and Dense Mapping from one Camera and an IMU
Media reports Hugging Face Papers Source language: Chinese
Accord builds accurate online dense metric maps from any camera‑IMU pair by anchoring keyframe windows to metric 3D points, using bidirectional dense depth agreement to correct scale errors, and fusing submaps in a factor graph, achieving top‑ranked 5 cm F‑score on several datasets.
Full text
Dense metric mapping from a single camera and IMU remains challenging: visual-inertial odometry (VIO) provides metric motion but sparse geometry, whereas feed-forward depth models predict dense structure without ensuring metric scale. We present Accord, which constructs an accurate online dense metric map from any camera with an IMU. A VIO filter publishes metric poses, a depth foundation model conditioned on them predicts depth for short keyframe windows, and a factor graph fuses the resulting submaps. Recent work has explored several approaches to this problem. What is essential is the multi-view agreement (Accord), which is considered in SLAM as a source of geometric self-consistency. Accord anchors each keyframe window to metric 3D points triangulated from the filter poses, then exploits bidirectional dense depth agreement between co-visible images to estimate and correct per-image scale errors while preserving the metric scale established by the anchors. Context keyframes further improve depth prediction, and the resulting submaps are fused in a factor graph. We evaluate a single mapping configuration across five public camera-IMU setups and a new Phone-rig/GoPro dataset. With nothing tuned per dataset/setup and every map aligned only by Accord's own trajectory, Accord achieves consistently best/second-best mean F-score at 5 cm on every platform. Accord is open-source along with the phone-rig dataset for the benefit of the research community
View arXiv page View PDF Project page GitHub 4 Add to collection