Forecasting Human Dynamics from Static Images
- 1 July 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 3643-3651
- https://doi.org/10.1109/cvpr.2017.388
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 structure recovery through quantitative and qualitative results.Keywords
This publication has 22 references indexed in Scilit:
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- End-to-End Learning of Action Detection from Frame Glimpses in VideosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- A Dual-Source Approach for 3D Pose Estimation from a Single ImagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Dense Optical Flow Prediction from a Static ImagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- 3D shape estimation from 2D landmarks: A convex relaxation approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Patch to the Future: Unsupervised Visual PredictionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- A Hierarchical Representation for Future Action PredictionLecture Notes in Computer Science, 2014
- Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural EnvironmentsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- From Actemes to Action: A Strongly-Supervised Representation for Detailed Action UnderstandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Articulated Human Detection with Flexible Mixtures of PartsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012