Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness

Abstract

Recently, convolutional networks (convnets) have proven useful for predicting optical flow. Much of this success is predicated on the availability of large datasets that require expensive and involved data acquisition and laborious la- beling. To bypass these challenges, we propose an unsuper- vised approach (i.e., without leveraging groundtruth flow) to train a convnet end-to-end for predicting optical flow be- tween two images. We use a loss function that combines a data term that measures photometric constancy over time with a spatial term that models the expected variation of flow across the image. Together these losses form a proxy measure for losses based on the groundtruth flow. Empiri- cally, we show that a strong convnet baseline trained with the proposed unsupervised approach outperforms the same network trained with supervision on the KITTI dataset.

Cited by in corpus (5)

• Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
• Optical Flow Estimation using a Spatial Pyramid Network
• TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation
• Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo Matching
• Large-Scale Mapping of Human Activity using Geo-Tagged Videos