Logo image
Back
Using deep learning to approximate joint placement in 3D bipedal characters
Thesis   Open access

Using deep learning to approximate joint placement in 3D bipedal characters

Andrew Dean Bishop
Master of Science (M.S.), Drexel University
Mar 2020
DOI:
https://doi.org/10.17918/00000225
pdf
Bishop_Andrew_20201.42 MBDownloadView
PDF Open Access Open Access (License Unspecified)

Abstract

Artificial Intelligence Three-dimensional imaging Deep learning (Machine learning) digital media Computer Animation
Throughout the History of 3D media production, rigging characters for animation has been a time intensive and technically complicated bottleneck in the production pipeline. A goal of tools creators has constantly been to create better tools to help make this process more accessible and faster. Many tools that are created focus on the creation of a control rig because it is the most easily automatable and the most technically involved step. However, before that step can be completed, the user must have a skeleton set up for a character. With the rise of machine learning techniques like deep learning and an increase in GPU power, the automation of skeleton creation and association has become more attainable. Through our research many attempts at automating the character deformations have been found, but there seem to be far fewer in terms of better automatic joint placement. This thesis proposes a method for creating a deep 3D convolutional neural network (3D-CNN) which can accurately place joints within a bipedal character based on the volume of its mesh. It focusses on bipedal characters with a specific set of joints to simplify the data collection and training processes. While the processes described in this paper could be greatly improved with more time, this serves as a proof of concept that 3D-CNNs can handle this task well.

Metrics

39 File views/ downloads
45 Record Views

Details

Logo image