Frankenstein re-mix fragment (after Whale)
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, F422182022-07-202022-07-202025-02-21Bibliographically approved