Many video enhancement algorithms rely on optical flow to register frames in a video sequence. Precise flow estimation is however intractable; and optical flow itself is often a sub-optimal representation for particular video processing tasks. In this paper, we propose task-oriented flow (TOFlow), a motion representation learned in a self-supervised, task-specific manner. We design a neural network with a trainable motion estimation component and a video processing component, and train them jointly to learn the task-oriented flow. For evaluation, we build Vimeo-90K, a large-scale, high-quality video dataset for low-level video processing. TOFlow outperforms traditional optical flow on standard benchmarks as well as our Vimeo-90K dataset in three video processing tasks: frame interpolation, video denoising/deblocking, and video super-resolution.
@article{arxiv.1711.09078,
title = {Video Enhancement with Task-Oriented Flow},
author = {Tianfan Xue and Baian Chen and Jiajun Wu and Donglai Wei and William T. Freeman},
journal= {arXiv preprint arXiv:1711.09078},
year = {2019}
}