# Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation

arXiv: https://arxiv.org/abs/1809.08317 · HTML: https://mlsanity.com/paper/1809.08317/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2018.

## Built on by (most cited first, 1 of 1)

- [A Perceptual Quality Metric for Video Frame Interpolation](https://mlsanity.com/paper/2210.01879/) (2022)

## Abstract (arXiv)

The difficulty of annotating training data is a major obstacle to using CNNs for low-level tasks in video. Synthetic data often does not generalize to real videos, while unsupervised methods require heuristic losses. Proxy tasks can overcome these issues, and start by training a network for a task for which annotation is easier or which can be trained unsupervised. The trained network is then fine-tuned for the original task using small amounts of ground truth data. Here, we investigate frame interpolation as a proxy task for optical flow. Using real movies, we train a CNN unsupervised for temporal interpolation. Such a network implicitly estimates motion, but cannot handle untextured regions. By fine-tuning on small amounts of ground truth flow, the network can learn to fill in homogeneous regions and compute full optical flow fields. Using this unsupervised pre-training, our network outperforms similar architectures that were trained supervised using synthetic optical flow.