ScopeFlow: Dynamic Scene Scoping for Optical Flow
| Autor: | Aviram Bar-Haim, Lior Wolf |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Optical flow Sampling (statistics) 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Regularization (mathematics) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data mining Artificial intelligence Adaptive optics business computer 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr42600.2020.00802 |
| Popis: | We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process. In addition, we find that both regularization and augmentation should decrease during the training protocol. Using an existing low parameters architecture, the method is ranked first on the MPI Sintel benchmark among all other methods, improving the best two frames method accuracy by more than 10%. The method also surpasses all similar architecture variants by more than 12% and 19.7% on the KITTI benchmarks, achieving the lowest Average End-Point Error on KITTI2012 among two-frame methods, without using extra datasets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|