Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Deep Learning Image Manipulation
Search
Leszek Rybicki
May 18, 2017
Research
2
210
Deep Learning Image Manipulation
Illustrated guide to some image manipulation methods, with demonstration.
Leszek Rybicki
May 18, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
130
How to Patch Image Classifiers
lunardog
0
2.2k
Towards Realistic Predictors - EN
lunardog
0
2.1k
Towards Realistic Predictors
lunardog
1
2.2k
Deep Learning Hot Dog Detector
lunardog
0
270
Finding beans in burgers: paper reading notes
lunardog
0
1.6k
Kelner: Serve Your Models
lunardog
0
120
Image Analysis at Cookpad
lunardog
1
1.8k
Kelner: serve your models
lunardog
1
380
Other Decks in Research
See All in Research
ストレス計測方法の確立に向けたマルチモーダルデータの活用
yurikomium
0
1.1k
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
740
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
160
問いを起点に、社会と共鳴する知を育む場へ
matsumoto_r
PRO
0
530
近似動的計画入門
mickey_kubo
4
1k
A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis
satai
3
250
Type Theory as a Formal Basis of Natural Language Semantics
daikimatsuoka
1
270
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
irvin
0
270
Towards a More Efficient Reasoning LLM: AIMO2 Solution Summary and Introduction to Fast-Math Models
analokmaus
2
720
Ad-DS Paper Circle #1
ykaneko1992
0
5.8k
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
540
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
14
9.5k
Featured
See All Featured
Facilitating Awesome Meetings
lara
54
6.5k
Designing for humans not robots
tammielis
253
25k
Building an army of robots
kneath
306
45k
Become a Pro
speakerdeck
PRO
29
5.5k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
760
Building a Scalable Design System with Sketch
lauravandoore
462
33k
Building Adaptive Systems
keathley
43
2.7k
Statistics for Hackers
jakevdp
799
220k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
36
2.5k
The Power of CSS Pseudo Elements
geoffreycrofte
77
5.9k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
Transcript
%FFQ-FBSOJOH *NBHF.BOJQVMBUJPO BOJMMVTUSBUFEHVJEF .-,JUDIFO
"CPVUNF w -FT[FL3ZCJDLJ w HJUIVC!MVOBSEPH w CPSOJO1PMBOE w .-3FTFBSDIFSBU$PPLQBE w
*MJLFOBUUP
DBSFFST!DPPLQBEDPN 8BOUUPXPSLXJUIVT
$POWPMVUJPOBM "SJUINFUJD OCIKE
*NBHFTUPGFBUVSFT
$POWPMVUJPO http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html input output input output kernel
4USJEF http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html 2px 2px 2px 2px
1BEEJOH http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html 2px 2px
4USJEF QBEEJOH http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html
5SBOTQPTFE http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html simulated here with padding also called “deconvolution” “fractional
stride”
%PXOTBNQMJOH features or small resolution image convolutional layer or layers
RGB image input output
6QTBNQMJOH upsampling CNN layer or layers RGB image features or
small resolution image input output
&ODPEFS%FDPEFS D E image in Decoder Encoder image out feature
space
'VMMZ$POOFDUFE $MBTTJpFS approve loan reject class data or features also
called “Dense” layer
$//$MBTTJpFS food person plant other AlexNet, LeNet, VGG…
'PPE/FU ™ food not food
@teenybiscuit
None
@teenybiscuit
@teenybiscuit
@teenybiscuit
@teenybiscuit
@teenybiscuit
(FOFSBUJWF "EWFSTBSJBM /FUXPSLT
Generator Discriminator https://speakerdeck.com/lunardog/deep-convolutional-voight-kampf-test “Couple of bots studying for the Turing
Test”
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec
Radford, Luke Metz, Soumith Chintala (Submitted on 19 Nov 2015 (v1), last revised 7 Jan 2016 (this version, v2)) https://arxiv.org/abs/1511.06434
Generator Discriminator G MPPLTMFHJU UPUBMMZTIPQQFE D
G SFBM GBLF D D(G(noise)) ˠ real (FOFSBUPSUSBJOJOH Discriminator acts
as the teacher
G SFBM GBLF D SFBM GBLF D D(G(noise)) ˠ fake
D(photo) ˠ real %JTDSJNJOBUPSUSBJOJOH Generator provides negative examples
None
https://www.youtube.com/watch?v=rs3aI7bACGc ©Yota Ishida
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec
Radford, Luke Metz, Soumith Chintala (Submitted on 19 Nov 2015 (v1), last revised 7 Jan 2016 (this version, v2)) https://arxiv.org/abs/1511.06434
$POEJUJPOBM ("/T
G NBMF GFNBMF DIJME FMEFSMZ G(noise | conditions) $POEJUJPOBM(FOFSBUPS
SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D $POEJUJPOBM%JTDSJNJOBUPS
SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D SJHIU XSPOH NBMF
GFNBMF DIJME FMEFSMZ SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D D
SJHIU XSPOH D $POEJUJPOBM("/ https://arxiv.org/abs/1411.1784 Conditional Generative Adversarial Nets Mehdi
Mirza, Simon Osindero (Submitted on 6 Nov 2014) Generator Discriminator NBMF GFNBMF DIJME FMEFSMZ G NBMF GFNBMF DIJME FMEFSMZ same condition
G NBMF GFNBMF DIJME FMEFSMZ SJHIU XSPOH NBMF GFNBMF DIJME
FMEFSMZ D $POEJUJPOBM("/ Discriminator Generator
https://www.faceapp.com/ Disclaimer: FaceApp authors don’t disclose their method. This is
only my guess. It may have nothing to do with GANs. original
original https://www.faceapp.com/
https://www.faceapp.com/ original
"SUJTUJD4UZMF5SBOTGFS Improved!
https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://arxiv.org/abs/1603.08155 transformation network loss network Gram matrices in feature space
pre-trained content image style image
“Gram matrices in feature space” https://en.wikipedia.org/wiki/Gramian_matrix
https://www.youtube.com/watch?v=xVJwwWQlQ1o
$ZDMF("/
https://github.com/junyanz/CycleGAN
https://github.com/junyanz/CycleGAN
https://github.com/junyanz/CycleGAN
(FOFSBUPS transformation network https://arxiv.org/abs/1603.08155
GBLF IPSTF GBLF IPSTF … %JTDSJNJOBUPS fully convolutional judges patches
of the input image https://arxiv.org/abs/1603.08155
"EWFSTBSJBM-PTT X F G Y GBLF [FCSB GBLF [FCSB …
GBLF IPSTF GBLF IPSTF … X(F(horse)) ˠ classify as zebra Y(F(zebra)) ˠ classify as horse
$ZDMF-PTT G F G(F(image))ˠ the same image F G F(G(image))ˠ
the same image
https://www.youtube.com/watch?v=9reHvktowLY
5IF&OE