Learning Based Image Synthesis and Manipulation
Covers ML-based synthesis and manipulation of images/videos using classical methods and deep learning models like ConvNets, GANs, and Diffusion Models.
Summary
What you’ll be able to do
Apply knowledge of basic theories, current approaches, key concepts, and common practices in the area of deep learning based image synthesis and manipulation.
Recognize and distinguish among a variety of image and video generation problems in computer vision, including their problem formulations and evaluation metrics.
Utilize and implement deep learning models to solve image and video generation problems.
Design deep learning models for image and video generation problems, conduct experiments to evaluate the proposed models, and analyze and interpret the results
Communicate effectively through written reports, oral presentations, and discussions.
Source: UW Guide
Grade history
↗No recorded grade history.
All recorded terms · compare terms & instructors
Prerequisites
Course mapGraduate/professional standing
- Graduate/professional standing
This is a best-effort interpretation; check the catalog requirements above.
Prerequisite text tree
- Graduate/professional standing
Professors
Spring 2027No instructors recorded for this selection.
Historical instructors & teaching patterns
Recorded history may be incomplete and does not establish a future schedule.
Calendar & sections
Spring 2027Schedule loads here as you scroll.
| Section | Mode | Enrolled / capacity | Waitlist |
|---|
Times are Central. Select a meeting for details; export includes recorded dates for the selected sections.
Meeting source records
No records available.
Student experience
the class
Introduces machine learning based synthesis and manipulation of visual data (images and videos). Both classical (e.g., nearest neighbor, filtering) and modern deep learning based (e.g., ConvNets, GANs, Diffusion Models) algorithms will be presented for image representation, synthesis, and manipulation. Usage of self-developed algorithms for image synthesis and manipulation to understand and analyze state-of-the-art techniques, and to identify interesting open questions and future directions.
difficulty & workload
No workload feedback recorded.
Topics
- Classical and deep learning algorithms for visual data
- Deep learning image synthesis and manipulation
- Image and video generation problem formulations
Skills
- Implementing deep learning models for image and video generation
- Formulating and evaluating image and video generation problems
- Designing models and analyzing experimental results
- Technical communication via reports and presentations
Grades
Grade distribution · % of letter grades
No grades available yet.
More grade details Grade mix, volume & source data
Sources & history
Catalog & offerings
Descriptions, prerequisites, and recorded course offerings.
Catalog observation history
Observations at scan time; dates do not imply when a catalog change took effect.
Selected offering source records
No offering records for the selected term.
Raw records
[]
Student reviews
Original comments behind the course and instructor summaries.
Read original reviews
No records available.
Grade history
Recorded grade distributions by term, section, and instructor.
Explore recorded gradesRecorded 2026-10-14
Model outputs & technical records
LLM outputs across runs
Full model traces
Recorded model configuration, reasoning, and tool conversations.
Model & dataset provenance
{
"model": "Qwen/Qwen3.8-27B",
"model_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
"task_version": "17",
"output_id": "e06f0079c3a327bdb06d8fd7530c89bd28bbd77a356a9b1583041a6972324168",
"requirements_status": "valid",
"dataset_revision": "fc1811fa52e581ea57a35c0cf3343f8740a8ffbf",
"observed_at": "2026-10-14 17:50:09.728220+00:00"
}