Context-aware Synthesis for Video Frame Interpolation

by   Simon Niklaus, et al.

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.



There are no comments yet.


page 1

page 5

page 7

page 8


Video Frame Interpolation via Adaptive Convolution

Video frame interpolation typically involves two steps: motion estimatio...

EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation

Video frame interpolation can up-convert the frame rate and enhance the ...

Depth-Aware Video Frame Interpolation

Video frame interpolation aims to synthesize nonexistent frames in-betwe...

TimeLens: Event-based Video Frame Interpolation

State-of-the-art frame interpolation methods generate intermediate frame...

CCVS: Context-aware Controllable Video Synthesis

This presentation introduces a self-supervised learning approach to the ...

Context-Aware Multipath Networks

Making a single network effectively address diverse contexts---learning ...

Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation

Given two consecutive frames, video interpolation aims at generating int...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.