Deep Fundamental Matrix Estimation Without Correspondences
| Autor: | Qiuren Fang, Aditya Prakash, Serge Belongie, Guandao Yang, Hanqing Jiang, Bharath Hariharan, Omid Poursaeed |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
Computer science business.industry Epipolar geometry Deep learning 02 engineering and technology 010501 environmental sciences 01 natural sciences Matrix (mathematics) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Fundamental matrix (computer vision) business Algorithm 0105 earth and related environmental sciences |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030110147 ECCV Workshops (3) |
| Popis: | Estimating fundamental matrices is a classic problem in computer vision. Traditional methods rely heavily on the correctness of estimated key-point correspondences, which can be noisy and unreliable. As a result, it is difficult for these methods to handle image pairs with large occlusion or significantly different camera poses. In this paper, we propose novel neural network architectures to estimate fundamental matrices in an end-to-end manner without relying on point correspondences. New modules and layers are introduced in order to preserve mathematical properties of the fundamental matrix as a homogeneous rank-2 matrix with seven degrees of freedom. We analyze performance of the proposed models using various metrics on the KITTI dataset, and show that they achieve competitive performance with traditional methods without the need for extracting correspondences. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|