Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.747524
Title: Assistive visual content creation tools via multimodal correlation analysis
Author: Hennessey, James W.
ISNI:       0000 0004 7231 173X
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2018
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
Visual imagery is ubiquitous in society and can take various formats: from 2D sketches and photographs to photorealistic 3D renderings and animations. The creation processes for each of these mediums have their own unique challenges and methodologies that artists need to overcome and master. For example, for an artist to depict a 3D scene in a 2D drawing they need to understand foreshortening effects to position and scale objects accurately on the page; or, when modeling 3D scenes, artists need to understand how light interacts with objects and materials, to achieve a desired appearance. Many of these tasks can be complex, time-consuming, and repetitive for content creators. The goal of this thesis is to develop tools to alleviate artists from some of these issues and to assist them in the creation process. The key hypothesis is that understanding the relationships between multiple signals present in the scene being created enables such assistive tools. This thesis proposes three assistive tools. First, we present an image degradation model for depth-augmented image editing to help evaluate the quality of the image manipulation. Second, we address the problem of teaching novices to draw objects accurately by automatically generating easy-to-follow sketching tutorials for arbitrary 3D objects. Finally, we propose a method to automatically transfer 2D parametric user edits made to rendered 3D scenes to global variations of the original scene.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.747524  DOI: Not available
Share: