Papers by Terence Broad
SIGGRAPH'17 Art Papers (Leonardo 50.4), 2017
‘Blade Runner—Autoencoded’ is a film made by training an autoencoder—a type of generative neural ... more ‘Blade Runner—Autoencoded’ is a film made by training an autoencoder—a type of generative neural network—to recreate frames from the film Blade Runner. The autoencoder is made to reinterpret every individual frame, reconstructing it based on its memory of the film. The result is a hazy, dreamlike version of the original film. The project explores the aesthetic qualities of the disembodied gaze of the neural network. The autoencoder is also capable of representing images from films it has not seen based on what it has learned from watching Blade Runner.
This project report describes a first approach to creating a visualisation of an artificial neura... more This project report describes a first approach to creating a visualisation of an artificial neural network, that visualises the topology of the network given an individual data input that the network has learned to recognise. A survey of previous attempts to visualise both artificial and biological neural networks is presented, as well as a survey of various techniques used in other forms of network visualisation that could be applied to visualising artificial neural networks. This is followed by a detailed description of the method implemented in this project, followed by results from the visualisation.
This report offers a first approach to the completion of light fields using the novel method of c... more This report offers a first approach to the completion of light fields using the novel method of constrained image synthesis and propagation through the focal stack.
Thesis Chapters by Terence Broad
This report details the implementation of an autoencoder trained with a learned similarity metric... more 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.
Uploads
Papers by Terence Broad
Thesis Chapters by Terence Broad