AutoFlow: Learning a Better Training Set for Optical Flow
2021
Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-Net and RAFT. Our code and data are available at this https URL .
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
52
References
5
Citations
NaN
KQI