Multi-encoder Network for Parameter Reduction of a Kernel-based Interpolation Architecture

TL;DR

This paper introduces a multi-encoder network that reduces parameters in a kernel-based video frame interpolation model, achieving better performance by using smaller encoders and rotation techniques.

Contribution

It proposes a novel parameter reduction method for a flow-less kernel-based interpolation network using multiple encoders and rotation to enhance feature learning.

Findings

Parameter reduction with smaller encoders improves efficiency.

The method outperforms the original network in accuracy.

Ablation studies justify design choices.

Abstract

Video frame interpolation involves the synthesis of new frames from existing ones. Convolutional neural networks (CNNs) have been at the forefront of the recent advances in this field. One popular CNN-based approach involves the application of generated kernels to the input frames to obtain an interpolated frame. Despite all the benefits interpolation methods offer, many of these networks require a lot of parameters, with more parameters meaning a heavier computational burden. Reducing the size of the model typically impacts performance negatively. This paper presents a method for parameter reduction for a popular flow-less kernel-based network (Adaptive Collaboration of Flows). Through our technique of removing the layers that require the most parameters and replacing them with smaller encoders, we reduce the number of parameters of the network and even achieve better performance compared to the original method. This is achieved by deploying rotation to force each individual encoder to learn different features from the input images. Ablations are conducted to justify design choices and an evaluation on how our method performs on full-length videos is presented.