用旋转感知提升图像匹配，让大规模三维重建更稳定可靠。
DINO-RotateMatch: A Rotation-Aware Deep Framework for Robust Image Matching in Large-Scale 3D Reconstruction
- 结合自监督全局描述符与旋转增强局部匹配
- 在Kaggle挑战赛中获得第47名（943支队伍）
- 适合需要高鲁棒性图像匹配的三维重建场景
本文提出DINO-RotateMatch，一种用于从非结构化互联网图像中进行大规模三维重建的深度学习框架。该方法融合数据集自适应图像配对策略与旋转感知的关键点提取及匹配机制。利用DINO检索大规模图像集合中语义相关的图像对，通过基于旋转的增强策略，结合ALIKED与Light Glue捕捉依赖方向的局部特征。在Kaggle图像匹配挑战赛2025上的实验表明，该方法在平均准确率（mAA）上持续提升，获得银奖（943支参赛队中排名第47）。结果证实，将自监督全局描述符与旋转增强的局部匹配相结合，可为大规模三维重建提供稳健且可扩展的解决方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。