DGC-Net: Dense Geometric Correspondence Network
This addresses the problem of handling large geometric transformations in image correspondence for computer vision applications, representing an incremental improvement over existing optical flow methods.
The paper tackles dense pixel correspondence estimation under strong geometric transformations by proposing a coarse-to-fine CNN framework that extends optical flow methods, achieving subpixel accuracy and outperforming existing dense approaches in relative camera pose estimation.
This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where ConvNets (CNNs) have recently achieved significant progress. While optical flow methods produce very accurate results for the small pixel translation and limited appearance variation scenarios, they hardly deal with the strong geometric transformations that we consider in this work. In this paper, we propose a coarse-to-fine CNN-based framework that can leverage the advantages of optical flow approaches and extend them to the case of large transformations providing dense and subpixel accurate estimates. It is trained on synthetic transformations and demonstrates very good performance to unseen, realistic, data. Further, we apply our method to the problem of relative camera pose estimation and demonstrate that the model outperforms existing dense approaches.