ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis

TL;DR

ConvTransformer introduces a novel convolutional Transformer architecture with multi-head self-attention for improved video frame synthesis, outperforming previous methods in quality and parallelization.

Contribution

This paper presents the first ConvTransformer architecture for video frame synthesis, combining convolutional and Transformer models with a new attention layer for better sequence learning.

Findings

Superior quality in video future frame extrapolation

More parallelizable than convolutional LSTM-based approaches

First application of ConvTransformer to video synthesis

Abstract

Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available, they work badly on video frame synthesis due to objects deforming and moving, scene lighting changes, and cameras moving in video sequence. In this paper, we present a novel and general end-to-end architecture, called convolutional Transformer or ConvTransformer, for video frame sequence learning and video frame synthesis. The core ingredient of ConvTransformer is the proposed attention layer, i.e., multi-head convolutional self-attention layer, that learns the sequential dependence of video sequence. ConvTransformer uses an encoder, built upon multi-head convolutional self-attention layer, to encode the sequential dependence between the input frames, and then a decoder decodes the long-term dependence between the target synthesized frames and the input frames. Experiments on video future frame extrapolation task show ConvTransformer to be superior in quality while being more parallelizable to recent approaches built upon convolutional LSTM (ConvLSTM). To the best of our knowledge, this is the first time that ConvTransformer architecture is proposed and applied to video frame synthesis.