2022f


Instructor
TA



MAT255 Techniques, History & Aesthetics of the Computational Photographic Image
George Legrady | http://vislab.mat.ucsb.edu
Yixuan Li 

Course materials are protected by US Copyright laws and by University policy. Contents of this course may not be reproduced, distributed, or displayed without my express prior written consent.

Tues-Thurs 1-2:50pm (some lectures may be online) otherwise Lab 2611, 2nd flr, ELings Hall
Course Information
An interdisciplinary course that examines, thorugh case studies, the state of the photographic image, its history, the theoretical, conceptual, and philosophical underpinnings. The course bridges studio arts, engineering, and humanities. This course may be of interest to artists, humanities researchers or programmers as there are three directions to explore:
  1. The aesthetic creative applications, opportunities and constraints,

  2. The computational processes from image processing to machine-learning, and

  3. The social considerations – to what degree can we believe in the image given the considerable software-based processing and autonomous image detail generation we are seeing through machine-learning processes.

The end goal is to investigate the photograph’s transformation through weekly presentations of projects, methods and discussion leading up to the impact of machine-learning on the creative process resulting in computational generated artworks.

Course Workload

 Attendance and participation at zoom lectures
Weekly contribution to course journal at Student Forum | Legal agreement
Final presentation pdf documentation of either a research paper OR project

09/22


 Course Overview, Apparatus Fundamentals
An overview of the optical-mechanical image capture machine
09/27



09/29

 Photographic History (1826 -1990)
A range of explorations from documentary, pictorialism, composite assembly, photograms, formal composition studies, etc.

Lab: MidJourney | Discord | Will Wulfken Reference | Projects
10/04



10/06

 Presentation of Equivalence, a voice-to-animation visualization 
George Legrady (Conceptual & Creative Direction), Dan Costa Baciu (NLP, Architecture design), Yixuan Li (Machine-learning, and Natural Language Processing Software Development) 

Lab: MidJourney | Diffusion Model Video 
10/11



10/13

 The Image as a DataStructure
Image as a Multi-Dimensional Data Structure | Interactive Convolution Neural Network | Aesthetic Primitives | Cohen's article about the image

Lab: MidJourney Presentation
10/18


10/20

 Signal & Noise/Glitch  
Information Theory’s noise and signal, randomness, Brownian motion, artistic exploration

Lab: Stable Diffusion
10/25


10/27

 Generative Art  |  Text-to-Image Creativity  | Gen Deep learning for Artistic Purposes
Rule-based artistic explorations

Lab: Stable Diffusion
11/01



11/03

 Image Generation, Deep Fakes, Social Implications
Humanities perspectives, news perspectives, use in arts and entertainment and business, applications of Deep Fakes

Lab: Stable Diffusion Presentation
11/08


11/10

 Machine-Learning, CNN, Deep Learning (Yixuan Li)
An introduction to machine-learning, convolutional neural networks

Lab: DALLE-2 
11/15

11/17

 Further discussion about Machine-learning (Yixuan Li)

Lab: DALLE-2
11/22

11/24

 THANKSGIVING

Lab: DALLE-2 Presentation
11/29

12/01
Lab: Final Project Work

Final Project Presentations
Student Projects
To be posted at end of the course