Comparing Correspondences: Video Prediction with Correspondence-wise Losses

04/19/2021
by   Daniel Geng, et al.
0

Today's image prediction methods struggle to change the locations of objects in a scene, producing blurry images that average over the many positions they might occupy. In this paper, we propose a simple change to existing image similarity metrics that makes them more robust to positional errors: we match the images using optical flow, then measure the visual similarity of corresponding pixels. This change leads to crisper and more perceptually accurate predictions, and can be used with any image prediction network. We apply our method to predicting future frames of a video, where it obtains strong performance with simple, off-the-shelf architectures.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset