Machine Learning
Neural Kubrick
Neural Kubrick is a video art project that examines the state of the art in Machine Learning, using the latest in "Deep Neural Network" techniques to reinterpret and redirect Kubrick’s films. In ‘2001: A Space Odyssey’, Stanley Kubrick speculated on the arrival of human-level artificial intelligence by the turn of the millennium.
The thesis project, conducted in the Interactive Architecture Lab at the Bartlett School of Architecture, examines how far AI has come and how it could change filmmaking itself. Three machine-learning algorithms take up the most significant roles in the AI film crew, those of art director, film editor, and director of photography.
​
Three iconic movies of Stanley Kubrick were used; namely, ‘2001 A Space Odyssey’, ‘A Clockwork Orange’ and ‘The Shining’. The output of these algorithms is a set of video sequences, where the machine as Art Director creates an alternative look and feel of the original video sequence, the machine as Film Editor creates an alternative parallel video sequence, and the machine as Director of Photography reshoots the same video sequence in virtual space from a machinic point of view.
Collaborators
Yulia Marouda and Hesham Hattab
Machine as Film Editor
​
​
A convolutional neural network takes up the role of a film editor that defines or classifies visual similarities between the given scene and a dataset of hundreds of different movies. A dataset of cinema frames was created from 100 movies. It consisted of extracted cinema frames of each movie, which summed up to around 115,000 images. The reverse image search algorithm was trained on this dataset. The interface, when queried with a movie clip, outputs a series of images which were similar to the input. A selection of movie frames was done, and a few seconds featuring those parts were clipped out from the original movie. All the clipped-out sequences were aligned together in relation to the input, and a parallel video was generated.
​
Machine as Director of Photography
​
​
A convolution Neural network takes up the role of a film editor that defines or classifies visual similarities between the given scene and a dataset of hundreds of different movies. A dataset of cinema frames was created from 100 movies, it consisted of extracted cinema frames of each movie which summed up to around 115,000 images. The reverse image search algorithm was trained on this dataset. The interface, when queried with a movie clip, outputS a series of images which were similar to the input. A selection of movie frames was done and few seconds featuring that parts were clipped out from the original movie. All the clipped-out sequences were aligned together in relation to the input and a parallel video was generated.
​
Machine as Art Director
​
A convolution Neural network takes up the role of a film editor that defines or classifies visual similarities between the given scene and a dataset of hundreds of different movies. A dataset of cinema frames was created from 100 movies, it consisted of extracted cinema frames of each movie which summed up to around 115,000 images. The reverse image search algorithm was trained on this dataset. The interface, when queried with a movie clip, outputS a series of images which were similar to the input. A selection of movie frames was done and few seconds featuring that parts were clipped out from the original movie. All the clipped-out sequences were aligned together in relation to the input and a parallel video was generated.
​
