Back to results

Massachusetts Institute of Technology

Text-Driven Movie Manipulation

Abstract

dc:description.abstract

In this thesis, we designed a method for manipulating a character’s appearance through a textual description of their desired appearance. Our method consisted of training a video-specific neural net model with an existing architecture for extracting keypoints, manipulating a representative frame to fit the user’s textual description through latent optimization, and producing a new video in a single forward pass. Our method requires an artist to follow 3 simple steps to manipulate a video and has only two inputs: a representative frame of the character the user wants to edit and a textual description of the desired appearance manipulation. Compared to work-intensive special effects, our method enables quick and flexible experimentation.

Degree

thesis:*
Name thesis:degree_name
Master
Department dc:contributor.department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Grantor dc:publisher
Massachusetts Institute of Technology
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Reyes Espinoza, Victor M.
Advisors dc:contributor.advisor
  • Materzynska, Joanna
  • Ma, Wei-Chiu
  • Torralba, Antonio

Rights

dc:rights
Statement dc:rights
  • In Copyright - Educational Use Permitted
  • Copyright MIT

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1721.1/144880
OAI identifier oai:identifier
oai:dspace.mit.edu:1721.1/144880

Chain of custody

source
Harvested from
MIT
Base URL
dspace.mit.edu/oai/request
Last updated
2026-07-22
Source record
OAI-PMH GetRecord
related terms
citation

Reyes Espinoza, Victor M.. Text-Driven Movie Manipulation. Massachusetts Institute of Technology, 2022. https://hdl.handle.net/1721.1/144880