Human Motion Prediction via Spatio-Temporal Inpainting

Abstract

We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively short periods of time (few hundred milliseconds) and typically ignore the absolute position of the skeleton w.r.t. the camera. Our scheme provides long term predictions (two seconds or more) for both the body pose and its absolute position. Our approach builds upon three main contributions. First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well. Secondly, we design an architecture to learn the joint distribution of body poses and global motion, capable to hypothesize large chunks of the input 3D tensor with missing data. And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. We propose two alternative metrics, based on the distribution of frequencies, that are able to capture more realistic motion patterns. Extensive experiments demonstrate our approach to significantly improve the state of the art, while also handling situations in which past observations are corrupted by occlusions, noise and missing frames.

arXiv comment8 pages

References in corpus (12)

• Sequence to Sequence Learning with Neural Networks
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Visualizing and Understanding Recurrent Networks
• Which Training Methods for GANs do actually Converge?
• Generative Image Inpainting with Contextual Attention
• Generalized Denoising Auto-Encoders as Generative Models
• A Deep Recurrent Framework for Cleaning Motion Capture Data
• A Neural Network Approach to Missing Marker Reconstruction in Human Motion Capture
• Low-rank passthrough neural networks
• Human Motion Analysis with Deep Metric Learning

Cited by in corpus (7)

• Convolutional Autoencoders for Human Motion Infilling
• DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
• PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
• Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation
• Long-term Human Motion Prediction with Scene Context
• DanceAnyWay: Synthesizing Beat-Guided 3D Dances with Randomized Temporal Contrastive Learning
• Human Motion Anticipation with Symbolic Label