Forecasting Human Dynamics from Static Images

2017/04/11 by Yu-Wei Chao, Chao, Yu-Wei, Yang, Jimei +6 · 4 citations
Computer Science · Engineering · #3D Shape Modeling and Analysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.1704.03432

openalex publication_date 2017/04/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D. To address the problem, we propose the 3D Pose Forecasting Network (3D-PFNet). Our 3D-PFNet integrates recent advances on single-image human pose estimation and sequence prediction, and converts the 2D predictions into 3D space. We train our 3D-PFNet using a three-step training strategy to leverage a diverse source of training data, including image and video based human pose datasets and 3D motion capture (MoCap) data. We demonstrate competitive performance of our 3D-PFNet on 2D pose forecasting and 3D pose recovery through quantitative and qualitative results.

Cited by

• mmPred: Radar-based Human Motion Prediction in the Dark
• Towards Consistent Long-Term Pose Generation
• Learning to Forecast and Refine Residual Motion for Image-to-Video Generation
• Learning to Generate Long-term Future via Hierarchical Prediction

Related

• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
• Learning 3D Human Dynamics from Video
• 3D Human Motion Prediction: A Survey
• Multi-Graph Convolution Network for Pose Forecasting
• TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting