# The Pose Knows: Video Forecasting by Generating Pose Futures

## TL;DR

This paper introduces a novel two-step approach to video forecasting that leverages human pose detection as an intermediate representation, improving prediction quality by modeling human movements in pose space before generating pixel-level videos.

## Contribution

The paper proposes a new method that combines a VAE for pose prediction with a GAN for pixel-level video generation, utilizing pose as an intermediate structured representation.

## Key findings

- Outperforms state-of-the-art video prediction methods
- Effectively models human movements in pose space
- Produces more interpretable and accurate video forecasts

## Abstract

Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model the forecasting problem at a higher level of abstraction. Specifically, we exploit human pose detectors as a free source of supervision and break the video forecasting problem into two discrete steps. First we explicitly model the high level structure of active objects in the scene---humans---and use a VAE to model the possible future movements of humans in the pose space. We then use the future poses generated as conditional information to a GAN to predict the future frames of the video in pixel space. By using the structured space of pose as an intermediate representation, we sidestep the problems that GANs have in generating video pixels directly. We show through quantitative and qualitative evaluation that our method outperforms state-of-the-art methods for video prediction.