DINO-RotateMatch: A Rotation-Aware Deep Framework for Robust Image Matching in Large-Scale 3D Reconstruction

TL;DR

DINO-RotateMatch is a deep learning framework that improves large-scale 3D reconstruction by combining dataset-adaptive image pairing, rotation-aware keypoint extraction, and matching, leading to more accurate image matching in unstructured internet image collections.

Contribution

It introduces a novel rotation-aware matching framework that integrates self-supervised global descriptors with rotation-enhanced local features for robust image matching.

Findings

Achieved a Silver Award in the Kaggle Image Matching Challenge 2025.

Demonstrated consistent improvements in mean Average Accuracy (mAA).

Validated robustness and scalability in large-scale 3D reconstruction tasks.

Abstract

This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet images. The method integrates a dataset-adaptive image pairing strategy with rotation-aware keypoint extraction and matching. DINO is employed to retrieve semantically relevant image pairs in large collections, while rotation-based augmentation captures orientation-dependent local features using ALIKED and Light Glue. Experiments on the Kaggle Image Matching Challenge 2025 demonstrate consistent improve ments in mean Average Accuracy (mAA), achieving a Silver Award (47th of 943 teams). The results confirm that combining self-supervised global descriptors with rotation-enhanced local matching offers a robust and scalable solution for large-scale 3D reconstruction.