AutoFlow: Learning a Better Training Set for Optical Flow

Deqing Sun, Daniel Vlasic, Charles Herrmann, Varun Jampani, Michael Krainin, Huiwen Chang, Ramin Zabih, William T. Freeman, Ce Liu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 10093-10102

Abstract

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 autoflow-google.github.io.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2021_CVPR, author = {Sun, Deqing and Vlasic, Daniel and Herrmann, Charles and Jampani, Varun and Krainin, Michael and Chang, Huiwen and Zabih, Ramin and Freeman, William T. and Liu, Ce}, title = {AutoFlow: Learning a Better Training Set for Optical Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {10093-10102} }