Skip to yearly menu bar Skip to main content


Learning Structure-from-Motion with Graph Attention Networks

Lucas Brynte · José Pedro Iglesias · Carl Olsson · Fredrik Kahl

Arch 4A-E Poster #90
[ ] [ Project Page ]
Wed 19 Jun 5 p.m. PDT — 6:30 p.m. PDT
Oral presentation: Orals 2B Deep learning architectures and techniques
Wed 19 Jun 1 p.m. PDT — 2:30 p.m. PDT


In this paper we tackle the problem of learning Structure-from-Motion (SfM) through the use of graph attention networks. SfM is a classic computer vision problem that is solved though iterative minimization of reprojection errors, referred to as Bundle Adjustment (BA), starting from a good initialization. In order to obtain a good enough initialization to BA, conventional methods rely on a sequence of sub-problems (such as pairwise pose estimation, pose averaging or triangulation) which provides an initial solution that can then be refined using BA. In this work we replace these sub-problems by learning a model that takes as input the 2D keypoints detected across multiple views, and outputs the corresponding camera poses and 3D keypoint coordinates. Our model takes advantage of graph neural networks to learn SfM-specific primitives, and we show that it can be used for fast inference of the reconstruction for new and unseen sequences. The experimental results show that the proposed model outperforms competing learning-based methods, and challenges COLMAP while having lower runtime.

Live content is unavailable. Log in and register to view live content