Corpus ID: 237490778

Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks

  title={Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks},
  author={Chunzhi Gu and Yan Zhao and Chao Zhang},
  • Chunzhi Gu, Yan Zhao, Chao Zhang
  • Published 2021
  • Computer Science
  • ArXiv
Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this paper, we propose a novel approach to predict future human motions from a much weaker condition, i.e., a single image, with mixture density networks (MDN) modeling. Contrary to most existing deep human motion prediction approaches, the multimodal nature of MDN… Expand


Deep Representation Learning for Human Motion Prediction and Classification
The results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction. Expand
Multi-level Motion Attention for Human Motion Prediction
This work proposes to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences to effectively exploit motion patterns from the long-term history to predict the future poses. Expand
HP-GAN: Probabilistic 3D Human Motion Prediction via GAN
A novel sequence-to-sequence model for probabilistic human motion prediction, trained with a modified version of improved Wasserstein generative adversarial networks (WGAN-GP), in which the model learns a probability density function of future human poses conditioned on previous poses. Expand
History Repeats Itself: Human Motion Prediction via Motion Attention
An attention-based feed-forward network is introduced that explicitly leverages the observation that human motion tends to repeat itself to capture motion attention to capture the similarity between the current motion context and the historical motion sub-sequences. Expand
Convolutional Sequence to Sequence Model for Human Dynamics
This work presents a novel approach to human motion modeling based on convolutional neural networks (CNN), which is able to capture both invariant and dynamic information of human motion, which results in more accurate predictions. Expand
On Human Motion Prediction Using Recurrent Neural Networks
It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction. Expand
Learning Trajectory Dependencies for Human Motion Prediction
A simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints, and design a new graph convolutional network to learn graph connectivity automatically. Expand
TrajeVAE - Controllable Human Motion Generation from Trajectories
A novel transformer-like architecture, TRAJEVAE, is proposed that outperforms trajectory-based reference approaches and methods that base their predictions on past poses in terms of accuracy and can predict reasonable future poses even if provided only with an initial pose. Expand
Structured Prediction Helps 3D Human Motion Modelling
A novel approach that decomposes the prediction into individual joints by means of a structured prediction layer that explicitly models the joint dependencies and increases the performance of motion forecasting irrespective of the base network, joint-angle representation, and prediction horizon. Expand
Predicting 3D Human Dynamics From Video
This work presents perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input, and inspired by the success of autoregressive models in language modeling tasks, learns an intermediate latent space on which to predict the future. Expand