Long-Term Video Generation of Multiple FuturesUsing Human Poses

04/16/2019
by   Naoya Fushishita, et al.
24

Predicting the near-future from an input 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 behaviors can possibly occur. Moreover, if the predicted future is too short, it may not be fully usable by a human or other system. In this paper, we propose a novel method for future video prediction capable of generating multiple long-term futures. This makes the predictions more suitable for real applications. First, from an input human video, we generate sequences of future human poses as the image coordinates of their body-joints by adversarial learning. We generate multiple futures by inputting to the generator combinations of 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.

READ FULL TEXT

page 1

page 3

page 6

research
04/16/2019

Long-Term Video Generation of Multiple Futures Using Human Poses

Predicting the near-future from an input video is a useful task for appl...
research
12/08/2020

Long Term Motion Prediction Using Keyposes

Long term human motion prediction is an essential component in safety-cr...
research
04/03/2018

When will you do what? - Anticipating Temporal Occurrences of Activities

Analyzing human actions in videos has gained increased attention recentl...
research
06/12/2018

Hierarchical Long-term Video Prediction without Supervision

Much of recent research has been devoted to video prediction and generat...
research
04/01/2021

TrajeVAE – Controllable Human Motion Generation from Trajectories

The generation of plausible and controllable 3D human motion animations ...
research
12/22/2020

Generating Long-term Continuous Multi-type Generation Profiles using Generative Adversarial Network

Today, the adoption of new technologies has increased power system dynam...
research
10/15/2019

Trajectorylet-Net: a novel framework for pose prediction based on trajectorylet descriptors

Pose prediction is an increasingly interesting topic in computer vision ...

Please sign up or login with your details

Forgot password? Click here to reset