Comparing Correspondences: Video Prediction with Correspondence-wise Losses
This addresses the issue of positional errors in video prediction for applications like video interpolation, though it is incremental as it modifies existing loss functions rather than introducing a new paradigm.
The paper tackles the problem of blurry predictions in video prediction tasks by proposing a correspondence-wise loss that matches images using optical flow and measures visual similarity of corresponding pixels, resulting in crisper and more perceptually accurate predictions without modifying the network architecture.
Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects 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 does not require modifications to the image prediction network. We apply our method to a variety of video prediction tasks, where it obtains strong performance with simple network architectures, and to the closely related task of video interpolation. Code and results are available at our webpage: https://dangeng.github.io/CorrWiseLosses