Long-term Human Motion Prediction with Scene Context
Authors:
Preprint
Abstract
Human movement is goal-directed and influenced by the spatial layout of the objects in the scene. To plan future human motion, it is crucial to perceive the environment -- imagine how hard it is to navigate a new room with lights off. Existing works on predicting human motion do not pay attention to the scene context and thus struggle in long-term prediction. In this work, we propose a novel three-stage framework that exploits scene context to tackle this task. Given a single scene image and 2D pose histories, our method first samples multiple human motion goals, then plans 3D human paths towards each goal, and finally predicts 3D human pose sequences following each path. For stable training and rigorous evaluation, we contribute a diverse synthetic dataset with clean annotations. In both synthetic and real datasets, our method shows consistent quantitative and qualitative improvements over existing methods.Keywords
All Related Versions
This publication has 43 references indexed in Scilit:
- Predicting Camera Viewpoint Improves Cross-Dataset Generalization for 3D Human Pose Estimation2020
- Learning to Forecast and Refine Residual Motion for Image-to-Video Generation2018
- Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera2018
- Integral Human Pose Regression2018
- Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World2018
- Learning Human Motion Models for Long-Term Predictions2017
- Social LSTM: Human Trajectory Prediction in Crowded Spaces2016
- Socially-Aware Large-Scale Crowd Forecasting2014
- Spatio-temporal motion tracking with unsynchronized cameras2012
- Social force model for pedestrian dynamicsPhysical Review E, 1995