Date of Publication

3-1-2019

Document Type

Master's Thesis

Degree Name

Master of Science in Computer Science

Subject Categories

Computer Sciences

College

College of Computer Studies

Department/Unit

Computer Science

Thesis Adviser

Arnulfo P. Azcarraga

Defense Panel Chair

Conrado D. Ruiz, Jr.

Defense Panel Member

Joel P. Ilao
Arnulfo P. Azcarraga

Abstract/Summary

dvancements on text-to-image synthesis generate remarkable images from tex-tual descriptions. However, these methods are designed to generate only one object with varying attributes. They face difficulties with complex descriptions having multiple arbitrary objects since it would require information on the place-ment and sizes of each object in the image. Recently, a method that infers object layouts from scene graphs has been proposed as a solution to this problem. How-ever, their method uses only object labels in describing the layout, which fail to capture the appearance of some objects. Moreover, their model is biased towards generating rectangular shaped objects in the absence of ground-truth masks. In this paper, we propose an object encoding module to capture object features and use it as additional information to the image generation network. We also intro-duce a graph-cuts based segmentation method that can infer the masks of objects from bounding boxes to better model object shapes. Our method produces more discernable images with more realistic shapes as compared to the images generated by the current state-of-the-art method.

Abstract Format

html

Language

English

Format

Electronic

Accession Number

CDTG007949

Keywords

Deep learning (Machine learning); Text data mining; Imaging systems

Upload Full Text

wf_yes

Embargo Period

12-1-2022

Download

Share

COinS