Jumping in at the Deep End: How to Experiment with Machine Learning in Post-Production Software


Recent years has seen an explosion in Machine Learning (ML)research. The challenge is now to transfer these new algorithms into the hands of artists and TD’s in visual effects and animation studios,so that they can start experimenting with ML within their existing pipelines. This paper presents some of the current challenges to experimentation and deployment of ML frameworks in the post-production industry. It introduces our open-source “ML-Server”client / server system as an answer to enabling rapid prototyping,experimentation and development of ML models in post-productionsoftware. Data, code and examples for the system can be found on the GitHub repository page:https://github.com/TheFoundryVisionmongers/nuke-ML-server


Computing methodologies→Machine learning;Software and its engineering→Software prototyping;
KEYWORDS deep learning, machine learning, visual computing, image processing, computer vision, deployment, integration, frameworks

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than theauthor(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. DigiPro ’19, July 27, 2019, Los Angeles, CA, USA©2019 Copyright held by the owner/author(s). Publication rights licensed to Associa-tion for Computing Machinery.ACM ISBN 978-1-4503-6799-8/19/07. . . $15.00

Voiced by Amazon Polly

  To access MetaSyst data, you must be logged in.

1 thought on “Jumping in at the Deep End: How to Experiment with Machine Learning in Post-Production Software”

Leave a comment