Long-Term Human Video Generation of Multiple Futures Using Poses

TL;DR

This paper introduces a novel method for long-term, multi-future human pose prediction from videos, utilizing adversarial learning with additional inputs to enhance diversity and realism, and generating future videos for practical applications.

Contribution

It proposes a new approach combining adversarial learning with latent codes and attraction points to predict diverse, long-term human poses and generate corresponding videos.

Findings

Outperforms state-of-the-art methods in realism, diversity, and accuracy.

Successfully predicts multiple long-term futures from a single input video.

Generates realistic future videos based on predicted human poses.

Abstract

Predicting future human behavior from an input human video is a useful task for applications such as autonomous driving and robotics. While most previous works predict a single future, multiple futures with different behavior can potentially occur. Moreover, if the predicted future is too short (e.g., less than one second), it may not be fully usable by a human or other systems. In this paper, we propose a novel method for future human pose prediction capable of predicting multiple long-term futures. This makes the predictions more suitable for real applications. Also, from the input video and the predicted human behavior, we generate future videos. First, from an input human video, we generate sequences of future human poses (i.e., the image coordinates of their body-joints) via adversarial learning. Adversarial learning suffers from mode collapse, which makes it difficult to generate a variety of multiple poses. We solve this problem by utilizing two additional inputs to the generator to make the outputs diverse, namely, a latent code (to reflect various behaviors) and an attraction point (to reflect various trajectories). In addition, we generate long-term future human poses using a novel approach based on unidimensional convolutional neural networks. Last, we generate an output video based on the generated poses for visualization. We evaluate the generated future poses and videos using three criteria (i.e., realism, diversity and accuracy), and show that our proposed method outperforms other state-of-the-art works.