FastJAM用图神经网络快速对齐多张图像，秒级完成且精度更高。
FastJAM: a Fast Joint Alignment Model for Images
- 基于现成匹配器和非参数聚类构建图像关键点关系图
- 通过图神经网络聚合对应关系，图像级池化预测单图变换矩阵
- 无需正则化项调参，训练时间从小时级缩短至秒级
图像联合对齐（JA）旨在将一组图像映射到统一坐标系，使语义相似特征位于对应空间位置。现有方法通常需要长时间训练、大模型容量和大量超参数调优。本文提出FastJAM，一种快速的基于图的方法，显著降低联合对齐任务的计算复杂度。FastJAM利用现成图像匹配器生成的成对匹配，结合快速非参数聚类，构建表征图像内与图像间关键点关系的图结构。图神经网络传播并聚合这些对应关系，通过图像级池化高效预测每张图像的单应性参数。采用逆复合损失函数，消除对预测变换施加正则化项的需求（从而也省去相关超参数调优）。实验表明，FastJAM在多个基准测试上优于现有主流方法，在对齐质量上表现更优，同时将计算时间从数分钟或数小时缩短至仅数秒。代码已公开于项目主页：https://bgu-cs-vil.github.io/FastJAM/
原文摘要 · Abstract (English)
Joint Alignment (JA) of images aims to align a collection of images into a unified coordinate frame, such that semantically-similar features appear at corresponding spatial locations. Most existing approaches often require long training times, large-capacity models, and extensive hyperparameter tuning. We introduce FastJAM, a rapid, graph-based method that drastically reduces the computational complexity of joint alignment tasks. FastJAM leverages pairwise matches computed by an off-the-shelf image matcher, together with a rapid nonparametric clustering, to construct a graph representing intra- and inter-image keypoint relations. A graph neural network propagates and aggregates these correspondences, efficiently predicting per-image homography parameters via image-level pooling. Utilizing an inverse-compositional loss, that eliminates the need for a regularization term over the predicted transformations (and thus also obviates the hyperparameter tuning associated with such terms), FastJAM performs image JA quickly and effectively. Experimental results on several benchmarks demonstrate that FastJAM achieves results better than existing modern JA methods in terms of alignment quality, while reducing computation time from hours or minutes to mere seconds. Our code is available at our project webpage, https://bgu-cs-vil.github.io/FastJAM/
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。