One-Step Time-Dependent Future Video Frame Prediction with a Convolutional Encoder-Decoder Neural Network

TL;DR

This paper introduces a CNN-based method for predicting future video frames at arbitrary time points, enabling more flexible anticipation of environmental changes for autonomous systems.

Contribution

It presents a novel approach that conditions CNN predictions on a continuous time variable, allowing future frame prediction at any specified time in the near future.

Findings

CNNs can learn intrinsic appearance change representations over time.

The method generates realistic future frame predictions at arbitrary time points.

It extends beyond next-frame prediction to flexible future anticipation.

Abstract

There is an inherent need for autonomous cars, drones, and other robots to have a notion of how their environment behaves and to anticipate changes in the near future. In this work, we focus on anticipating future appearance given the current frame of a video. Existing work focuses on either predicting the future appearance as the next frame of a video, or predicting future motion as optical flow or motion trajectories starting from a single video frame. This work stretches the ability of CNNs (Convolutional Neural Networks) to predict an anticipation of appearance at an arbitrarily given future time, not necessarily the next video frame. We condition our predicted future appearance on a continuous time variable that allows us to anticipate future frames at a given temporal distance, directly from the input video frame. We show that CNNs can learn an intrinsic representation of typical appearance changes over time and successfully generate realistic predictions at a deliberate time difference in the near future.