用多视角变换假设加速特征匹配，速度提升4倍且精度不降。
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
- 构建多个单应性假设逼近真实对应关系，结合单向交叉注意力提速。
- 在YFCC100M上精度媲美LoFTR，推理速度提升4倍。
- 适合需要高速高精度匹配的视觉任务，如SLAM与三维重建。
针对学习式局部特征匹配的效率问题，本文提出一种高效的基于Transformer的网络架构。该方法通过构建多个单应性假设来近似真实世界中的连续对应关系，并采用单向交叉注意力机制加速匹配优化。在YFCC100M数据集上，该方法的匹配精度与当前最先进的基于Transformer的LoFTR相当，而推理速度提升至4倍，甚至超越部分基于CNN的方法。在Megadepth、ScanNet和HPatches等多个公开数据集上的全面评估验证了其有效性，表明该方法在多种下游应用中具有显著提升潜力。
原文摘要 · Abstract (English)
We tackle the efficiency problem of learning local feature matching. Recent advancements have given rise to purely CNN-based and transformer-based approaches, each augmented with deep learning techniques. While CNN-based methods often excel in matching speed, transformer-based methods tend to provide more accurate matches. We propose an efficient transformer-based network architecture for local feature matching. This technique is built on constructing multiple homography hypotheses to approximate the continuous correspondence in the real world and uni-directional cross-attention to accelerate the refinement. On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods. Comprehensive evaluations on other open datasets such as Megadepth, ScanNet, and HPatches demonstrate our method's efficacy, highlighting its potential to significantly enhance a wide array of downstream applications.
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。