Score: 0

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

Published: December 3, 2025 | arXiv ID: 2512.03715v1

By: Kaichen Zhang, Tianxiang Sheng, Xuanming Shi

Potential Business Impact:

Helps computers build 3D worlds from internet pictures.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Page Count
9 pages

Category
Computer Science:
CV and Pattern Recognition