Manipulating space and time in visual media
Abstract/Contents
- Abstract
- With the increased usage of digital technology, visual media has become a popular form of communication and is widely used for storytelling and art. Often times, authors of visual media may wish to make spatial or temporal edits in post-production. However, it can be difficult to author edits while preserving realism. One main issue is that there are many constraints involved in realism, which limit the edits that can be achieved given user-specified inputs. Moreover, often times these constraints are not explicitly defined. In this work, we introduce task-dependent realism, which explicitly defines realism for a target manipulation task. We focus on two manipulation tasks and identify spatial and temporal properties to relax to achieve a greater number of realistic-looking edits. This thesis contributes: 1) spatial and temporal constraints to relax and maintain for two manipulation tasks, based on perceptual properties; and 2) techniques which automatically maintain and relax these constraints as the user specifies input constraints and explores edits.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2023; ©2023 |
Publication date | 2023; 2023 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Liu, Sean Jeng | |
---|---|---|
Degree supervisor | Agrawala, Maneesh | |
Thesis advisor | Agrawala, Maneesh | |
Thesis advisor | Hertzmann, Aaron | |
Thesis advisor | Landay, James A, 1967- | |
Degree committee member | Hertzmann, Aaron | |
Degree committee member | Landay, James A, 1967- | |
Associated with | Stanford University, School of Engineering | |
Associated with | Stanford University, Computer Science Department |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Sean J. Liu. |
---|---|
Note | Submitted to the Computer Science Department. |
Thesis | Thesis Ph.D. Stanford University 2023. |
Location | https://purl.stanford.edu/qg406gc5383 |
Access conditions
- Copyright
- © 2023 by Sean Jeng Liu
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...