CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching
cs.RO, cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Comments: Accepted by CoRL 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation.
Terminology
Abstract
Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation. Existing semi-dense matchers predict confidence on fixed grids, limiting correspondences to predefined locations and requiring costly high-resolution grids for precise localization. We present CoReMatch (Coordinate Refinement Match), a recurrent framework that refines correspondences directly in continuous coordinate space rather than predicting discrete confidence maps. CoReMatch progressively improves correspondence estimates by propagating information across iterations. At the coarse stage, a Deep Aggregated Transformer captures global context and iteratively updates correspondence coordinates, while a lightweight regression head further sharpens their localization. Experiments on indoor and outdoor benchmarks show that CoReMatch strikes a strong balance between accuracy and efficiency, outperforming Efficient LoFTR in accuracy while running more than 10x faster on embedded edge hardware. These results demonstrate that recurrent coordinate refinement offers an efficient and scalable approach to real-time feature matching for robotic perception.
Sources
- QuadTree Attention for Vision Transformers
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- DINOv2: Learning Robust Visual Features without Supervision
- Decoupled Weight Decay Regularization
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation