Autoencoding Video Frames

Broad, Terence and Grierson, Mick. 2016. Autoencoding Video Frames. Technical Report. Goldsmiths, London. [Report]

Autoencoding_Video_Frames.pdf - Published Version
Available under License Creative Commons Attribution.

Download (47MB) | Preview

Abstract or Description

This report details the implementation of an autoencoder trained with a learned similarity metric - one that is capable of modelling a complex dis- tribution of natural images - training it on frames from selected films, and using it to reconstruct video sequences by passing each frame through the autoencoder and re-sequencing the output frames in-order. This is primarily an artistic exploration of the representational capacity of the current state of the art in generative models and is a novel application of autoencoders. This model is trained on, and used to reconstruct the films Blade Runner and A Scanner Darkly, producing new artworks in their own right. Experiments passing other videos through these models is carried out, demonstrating the potential of this method to become a new technique in the production of experimental image and video.

Item Type:

Report (Technical Report)

Departments, Centres and Research Units:



12 May 2016

Item ID:


Date Deposited:

27 Jan 2017 17:57

Last Modified:

29 Apr 2020 16:23


View statistics for this item...

Edit Record Edit Record (login required)