FastJAM: a Fast Joint Alignment Model for Images

TL;DR

FastJAM is a rapid, graph-based joint image alignment method that significantly reduces computation time while improving alignment quality, using a graph neural network and inverse-compositional loss to simplify training.

Contribution

FastJAM introduces a novel, fast joint alignment approach that leverages pairwise matches, graph neural networks, and an inverse-compositional loss to enhance efficiency and accuracy.

Findings

Outperforms existing methods in alignment quality.

Reduces computation time from hours/minutes to seconds.

Eliminates hyperparameter tuning with inverse-compositional loss.

Abstract

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/