Convolutional Autoencoders for Human Motion Infilling

TL;DR

This paper introduces a convolutional autoencoder model for human motion infilling that can generate smooth, natural transitions between motion sequences, handle partial data, and fill gaps of varying lengths without post-processing.

Contribution

The paper presents a novel end-to-end convolutional autoencoder approach that treats motion infilling as an inpainting problem, capable of handling diverse gap scenarios in 3D human motion data.

Findings

The model effectively fills in missing motion frames with natural transitions.

It can handle partial poses and noise in motion data.

The approach works for gaps of arbitrary length and type.

Abstract

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.