Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness
Computer Vision - ECCV 2016 Workshops, Pt III(2016)
摘要
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.
更多查看译文
关键词
Optical Flow,Image Pair,Contractive Part,Unsupervised Approach,Flow Prediction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络