Guided Optical Flow Learning

02/08/2017
by   Yi Zhu, et al.
0

We study the unsupervised learning of CNNs for optical flow estimation using proxy ground truth data. Supervised CNNs, due to their immense learning capacity, have shown superior performance on a range of computer vision problems including optical flow prediction. They however require the ground truth flow which is usually not accessible except on limited synthetic data. Without the guidance of ground truth optical flow, unsupervised CNNs often perform worse as they are naturally ill-conditioned. We therefore propose a novel framework in which proxy ground truth data generated from classical approaches is used to guide the CNN learning. The models are further refined in an unsupervised fashion using an image reconstruction loss. Our guided learning approach is competitive with or superior to state-of-the-art approaches on three standard benchmark datasets yet is completely unsupervised and can run in real time.

READ FULL TEXT
research
09/21/2018

Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation

The difficulty of annotating training data is a major obstacle to using ...
research
09/12/2017

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

This paper develops an unsupervised learning algorithm that trains a Dee...
research
09/02/2020

When Deep Learning Meets Digital Image Correlation

Convolutional Neural Networks (CNNs) constitute a class of Deep Learning...
research
07/27/2023

BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning

In the field of phase change phenomena, the lack of accessible and diver...
research
07/21/2023

Selecting the motion ground truth for loose-fitting wearables: benchmarking optical MoCap methods

To help smart wearable researchers choose the optimal ground truth metho...
research
08/20/2018

FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images

Recent work has shown that convolutional neural networks (CNNs) can be u...
research
06/16/2020

End-to-End Real-time Catheter Segmentation with Optical Flow-Guided Warping during Endovascular Intervention

Accurate real-time catheter segmentation is an important pre-requisite f...

Please sign up or login with your details

Forgot password? Click here to reset