2. Presentation Outline
Introduction
Statement of problem
Objective
Scope, constraints & contribution
Related works
Theoretical & conceptual framework
Proposed Methods
Thesis budget and schedule timeline
Conclusion
2
3. 33
Domains in the fashion design requires
Effective interactive Design
Interactive design may applied in
Clothing and painting art
Building and home utility products
This can be achieve using generative model approach giving user given
input for product category
Introduction
4. 44
Generating conditioned image
Color
shape
style
Pattern
texture etc.)
Improve some nose and artifacts
Pull to public cloth dataset
Motivation
5. 55
challenging task
hag subjectivity
Focus on designer interest
(no more creativity) and Difficult to
share style
Difficulties in training and produce
high-resolution.[2]
Statement of problem
6. 66
Here are research question
REQ1: What are the effective ways to interactive fashion design?
REQ2: What kind proposed solution to be used for generation of image for
better interactive design?
REQ3: How the quality of generated fashion design can be improved and
comparison of results based evaluation metrics?
Research Question
7. 77
Design and develop visual aware interactive fashion design framework
through deep generative network to improve quality and fine-grained style.
General Objective
8. 88
Specific Objective
Here are list of specific objective
Investigate the domain using Systematic Literature review
Collect dataset from different source
Prepare annotation and preprocessing the data
Create a fusion CGAN and SRGAN
Train the model and feed the data
Present the result and evaluate model
9. 99
Scope
Here are list of scope of research
Collecting and pre-processing the dataset
Creating a fusion of conditional GAN ,where it easy for controlling and
SRGAN to enhance the quality of generated image
Present result and evaluation result
Constraints
No sufficient dataset available
lack of high computational resource(GPU) .
10. 1010
[2] Kang et.al Visually-Aware Fashion Recommendation and Design with
Generative Image Models.
Methods :GAN
Objective : suggesting existing items on fashion images for both prediction
and design
Gap(future research) :
Poor quality and
difficult control fine-grained style
Related works
11. 1111
Related works
[5] Y. R et.al (2018) FashionGAN: Display your fashion design using
Conditional Generative Adversarial Nets
Methods :FashionGAN
Objective :Automatically generated fashion image and establishes a
bijection relationship between generated image .
Gap(future research) :
workable for single-color and regular
it cannot map an irregular one with multiple colors and style
Needed further research
12. 1212
Related works
Author and Title Methodology Objective GAP(future work)
[1] Yildirim et.al (2019)
Generating High-
Resolution Fashion Model
Images Wearing Custom
Outfits
unconditional
Conditional
GAN
Transfer the
style/color
generate images
of fashion models
• Quality is not good
and consistent
model
[3] Christoph et. Al A
Generative Model of
People in Clothing
• graphics
pipeline
design and
• 3D data
acquisition
Semantic
segmentation
prediction
texture prediction
• High
computational
resources for
rendering
13. 1313
Related works cont...d
Author and Title Methodology Objective GAP(future work)
[4] Zhu et.al (2017)
Be Your Own Prada:
Fashion Synthesis with
Structural Coherence
semantic
segmentation
map.
compositional
mapping layer
collecting
sentence
• model
can also render textured
background .
• Do not post
processing of
the background
[6] Pandey
et al (2019)Poly-gan:
Multi-conditioned Gan
For Fashion Synthesis
• Poly-GAN multiple inputs and is
suitable for many
tasks, image
alignment, image
stitching and
inpainting
Design
architecture to
apply for a variety
of applications.
14. 1414
Theoretical framework of GAN
CGAN is very similar to GAN, except both
the generator and discriminator are
conditioned on some extra information, y.
Gan’s have two networks
1.Generator G takes some random
noise and tries to produce real input
training images by fooling the
discriminator D.
2.Discriminator D tries to classify the
input being real if it’s coming from the
training data and fake if it’s coming
from the generator G.
15. 1515
Methodology
Dataset
Scrapping website like pintrest , esy.com
Download from channel and page
Request image from fashion studio
Capture image
Preprocessing
Augmentation, Scaling , background
Feature extraction
GaitGAN:[34] is used to reduce the effect
of variations
PCA-> to reduce the dimension
1
PreprocessingDataset
2
Feature Ex and Red
3 4
Train for
CGAN
Train for
SRGAN
Present
result
5 6
16. 1616
LR image
HR image
generator
High quality fake or real
Dataset
Proposed architecture workflow
Xr
Y
Y
Z
Generator
Discriminator
Generator
Discriminator
D
D
A Generator(An artist) neural network.
•Discriminator has to
correctly label real images
which are coming from
training data set as “real”.
17. 1717
Cont...d
CGAN for generating condition fashion images
SRGAN to Refine the quality from generated one
Nobility
Enhancement of Quality image
control fine-grained style
Improve to work with multiple
color
19. 1919
Contribution and application of result
Collecting dataset and pull to github
Creating of fusion algorithm CGAN and SRGAN
Enhance quality generated image(SRGAN) and Control fine grained style
(CGAN)
Application of result
Style transfer across multiple domain image generation
Image to image translation :learn mapping input and output
photo editing and image enhancement
20. 2020
Budget plan (operation cost)
Operation cost
Item No Item Name Unit price Quantity * unit Total Source
1 Data collection 2000 3*2000 6000
Coveredby
Researchfund
2 Data preparation 1500 3*1500 4500
3 Print cost and binding 650 4*650 2600
3 Transport cost 300 6*300 1800
5 Contingency plan (10%) 10% 1*2500 2500
Total operation cost 14700
Total material cost 7800
Total cost operation +material _contingency =25,000 ETB
Material cost
Item no Item name Specification Unit price Qty. Total
1 GPU MSI RTX 2070 250$ 1 -
2 Flash USB SanDisk 32GB 10$ 1 -
Total 210 USD =7800 ETB
21. 2121
July 2019 days Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun
Literature review 334
Writing Proposal 99
Proposal defense -
Data collection 120
Data preparation 50
Train model 60
Verify the model 90
Result Report and
summarization
90
TodayTodayCompleteComplete IncompleteIncomplete Not StartedNot Started
2020
June 2020
Months
Research timeline and schedule