Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Frankenstein re-mix fragment (after Whale)
Stockholm University of the Arts, Department of Film and Media.ORCID iD: 0000-0001-5878-3157
2022 (English)Artistic output (Unrefereed)
Resource type
Moving image
Physical description [en]

A .mp4 movie file of 9.34 MB or 9,799,171 bytes.

Description [en]

Frankenstein re-mix fragment (after Whale) 2022.

#AI #Art #MachineLearning #Artistry #Cinema #FoundFootage #GenerativeAdversialNetwork #GAN #KinoAusZweiterHand #PostBlümlinger #Re- #Remploi #MarcJohnson

A narrative film using a Generative Adversarial Network for Face Anonymization that reinforces the uncanny of a 1931 movie — where an obsessed scientist creates a living being from body parts, not realizing it has a madman's brain. Who is the madman here?

Methodology

1. Install cuda 11.6 installer

2. Install cuda available torch using pip

3. pip3 install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu116

4. Install python

5. pip3 install -r requirements.txt (in repo)

6. Virtual camera [OBS] for webcam.py7a. python .\anonymize.py  -s "<path_to_input_folder>" -m <model_name>` Model name is optional.7b. python .\webcam.py -m <model_name>` Model name is optional./ Models

Model • Dataset • Detector • Num parameters

• d_p_v1 • FDF 128x128 • DSFD face detector + Mask RCNN for keypoints • 46.92M• fdf128_rcnn512 • FDF 128x128|DSFD face detector + Mask RCNN for keypoints • 47.39M• fdf128_retinanet512 • FDF 128x128 • SSD-based RetinaNet with ResNet50 backbone • 49.84M• fdf128_retinanet256 • FDF 128x128 • SSD-based RetinaNet with ResNet50 backbone • 12.704M• fdf128_retinanet128 • FDF 128x128 • SSD-based RetinaNet with ResNet50 backbone • 3.17M

Abstract [en]

A narrative film using a Generative Adversarial Network for Face Anonymization that reinforces the uncanny of a 1931 movie — where an obsessed scientist creates a living being from body parts, not realizing it has a madman's brain. Who is the madman here?

Place, publisher, year, pages
Stockholm, 2022.
Keywords [en]
AI, Art, Machine learning, machine vision, artistry, cinema, found footage, generative adversarial network, Gan, Kino Aus Zweiter Hand, Post Blümlinger, Re-, Remploi, Marc Johnson
National Category
Visual Arts Studies on Film Computer graphics and computer vision
Research subject
Artistic practices; Third-Cycle Studies in Performative and Mediated Practices
Identifiers
URN: urn:nbn:se:uniarts:diva-1276OAI: oai:DiVA.org:uniarts-1276DiVA, id: diva2:1683947
Projects
DeepPrivacy
Funder
Stockholm University of the Arts, F42218Available from: 2022-07-20 Created: 2022-07-20 Last updated: 2025-02-21Bibliographically approved

Open Access in DiVA

Frankenstein-re-mix-fragment(9570 kB)48 downloads
File information
File name MOVIE01.mp4File size 9570 kBChecksum SHA-512
e602f966524da94a40c91d400b82b84a0ab6c24779ff49704cc1a25b02fd97a51bc3cb3585830a675edaceee877534f16fabdd5e14ee921333cb7b048cb88a09
Type movieMimetype video/mp4

Search in DiVA

By author/editor
Johnson, Marc
By organisation
Department of Film and Media
Visual ArtsStudies on FilmComputer graphics and computer vision

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 306 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf