Convolutional Autoencoders for Human Motion Infilling

10/22/2020
by   Manuel Kaufmann, et al.
0

In this paper we propose a convolutional autoencoder to address the problem of motion infilling for 3D human motion data. Given a start and end sequence, motion infilling aims to complete the missing gap in between, such that the filled in poses plausibly forecast the start sequence and naturally transition into the end sequence. To this end, we propose a single, end-to-end trainable convolutional autoencoder. We show that a single model can be used to create natural transitions between different types of activities. Furthermore, our method is not only able to fill in entire missing frames, but it can also be used to complete gaps where partial poses are available (e.g. from end effectors), or to clean up other forms of noise (e.g. Gaussian). Also, the model can fill in an arbitrary number of gaps that potentially vary in length. In addition, no further post-processing on the model's outputs is necessary such as smoothing or closing discontinuities at the end of the gap. At the heart of our approach lies the idea to cast motion infilling as an inpainting problem and to train a convolutional de-noising autoencoder on image-like representations of motion sequences. At training time, blocks of columns are removed from such images and we ask the model to fill in the gaps. We demonstrate the versatility of the approach via a number of complex motion sequences and report on thorough evaluations performed to better understand the capabilities and limitations of the proposed approach.

READ FULL TEXT

page 4

page 5

page 7

page 12

research
06/14/2022

Recurrent Transformer Variational Autoencoders for Multi-Action Motion Synthesis

We consider the problem of synthesizing multi-action human motion sequen...
research
08/31/2023

Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction

A new method is proposed for human motion prediction by learning tempora...
research
03/29/2022

Long-term Video Frame Interpolation via Feature Propagation

Video frame interpolation (VFI) works generally predict intermediate fra...
research
04/04/2022

HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE

Studies on the automatic processing of 3D human pose data have flourishe...
research
06/15/2019

An End-to-End Block Autoencoder For Physical Layer Based On Neural Networks

Deep Learning has been widely applied in the area of image processing an...
research
12/09/2017

A Deep Recurrent Framework for Cleaning Motion Capture Data

We present a deep, bidirectional, recurrent framework for cleaning noisy...
research
04/10/2017

Learning Human Motion Models for Long-term Predictions

We propose a new architecture for the learning of predictive spatio-temp...

Please sign up or login with your details

Forgot password? Click here to reset