# Context-aware Synthesis for Video Frame Interpolation

## TL;DR

This paper introduces a context-aware neural network approach for video frame interpolation that leverages pixel-wise contextual information and bidirectional optical flow to produce high-quality intermediate frames, especially in challenging scenarios.

## Contribution

It proposes a novel context-aware synthesis method that uses pixel-wise context maps and end-to-end training to improve frame interpolation quality over existing techniques.

## Key findings

- Outperforms state-of-the-art methods in handling occlusion and large motion.
- Effectively uses contextual information for more accurate frame synthesis.
- Demonstrates robustness in challenging video scenarios.

## Abstract

Video frame interpolation algorithms typically estimate optical flow or its variations and then use it to guide the synthesis of an intermediate frame between two consecutive original frames. To handle challenges like occlusion, bidirectional flow between the two input frames is often estimated and used to warp and blend the input frames. However, how to effectively blend the two warped frames still remains a challenging problem. This paper presents a context-aware synthesis approach that warps not only the input frames but also their pixel-wise contextual information and uses them to interpolate a high-quality intermediate frame. Specifically, we first use a pre-trained neural network to extract per-pixel contextual information for input frames. We then employ a state-of-the-art optical flow algorithm to estimate bidirectional flow between them and pre-warp both input frames and their context maps. Finally, unlike common approaches that blend the pre-warped frames, our method feeds them and their context maps to a video frame synthesis neural network to produce the interpolated frame in a context-aware fashion. Our neural network is fully convolutional and is trained end to end. Our experiments show that our method can handle challenging scenarios such as occlusion and large motion and outperforms representative state-of-the-art approaches.