An End to End Network Architecture for Fundamental Matrix Estimation
This work addresses the problem of robust fundamental matrix estimation for computer vision applications, representing an incremental advancement in deep learning-based approaches.
The authors tackled fundamental matrix estimation from stereo images by developing an end-to-end network architecture that integrates correspondence finding, outlier rejection, and matrix calculation, achieving significant performance improvements over traditional and previous deep learning methods on various metrics.
In this paper, we present a novel end-to-end network architecture to estimate fundamental matrix directly from stereo images. To establish a complete working pipeline, different deep neural networks in charge of finding correspondences in images, performing outlier rejection and calculating fundamental matrix, are integrated into an end-to-end network architecture. To well train the network and preserve geometry properties of fundamental matrix, a new loss function is introduced. To evaluate the accuracy of estimated fundamental matrix more reasonably, we design a new evaluation metric which is highly consistent with visualization result. Experiments conducted on both outdoor and indoor data-sets show that this network outperforms traditional methods as well as previous deep learning based methods on various metrics and achieves significant performance improvements.