# Geometry-Aligned Semantic Matching for Cross-Modal Planar Image Registration

arXiv: https://arxiv.org/abs/2610.03167 · HTML: https://mlsanity.com/paper/2610.03167/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 25 of 25)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [XoFTR: Cross-modal Feature Matching Transformer](https://mlsanity.com/paper/2404.09692/) (2024)
- [MINIMA: Modality Invariant Image Matching](https://mlsanity.com/paper/2412.19412/) (2024)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [A Mixed Diet Makes DINO An Omnivorous Vision Encoder](https://mlsanity.com/paper/2602.24181/) (2026)
- [MM-OVSeg:Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing](https://mlsanity.com/paper/2603.17528/) (2026)
- [SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotation](https://mlsanity.com/paper/2604.13941/) (2026)
- [Grid-Reg: Detector-Free Gridized Feature Learning and Matching for Large-Scale SAR-Optical Image Registration](https://mlsanity.com/paper/2507.04233/) (2025)
- [AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images](https://mlsanity.com/paper/2606.31077/) (2026)

## Abstract (arXiv)

Cross-modal image matching establishes stable and accurate geometric correspondences across modalities for planar registration. Existing semantic representations provide cross-modal consistency, but semantic similarity does not necessarily imply geometric correspondence. Meanwhile, fine-grained CNN features provide accurate local details but lack global cross-modal semantic guidance for stable refinement. To address these issues, we propose CDPM, which first establishes geometrically consistent semantic representations and then preserves their dominant role in correspondence estimation during fine-grained localization. Specifically, we progressively adapt DINOv3 using geometrically consistent cross-modal patch pairs, enabling feature similarity to better reflect true cross-modal spatial correspondences. We then construct a DINO-Centric Feature Pyramid, where multi-scale DINO representations maintain stable cross-modal correspondences, while a lightweight CNN branch provides auxiliary structural details for precise local refinement. Extensive experiments on three cross-modal datasets demonstrate the superior performance of CDPM. On VIS-IR, compared with the dense matcher RoMa, CDPM improves AUC@3/5/10/20 by 7.36, 13.40, 13.75, and 10.42 percentage points, respectively, and reduces mACE from 5.83 to 2.78 pixels. It also outperforms RoMa v2 across all metrics while requiring 45.6% fewer FLOPs. The online demo and dataset are available, and the code will be released on our project page at https://warren-wzw.github.io/CDPM/.