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
Synthesizing Human Images in SIGGRAPH Asia 2021
Search
Udon
February 27, 2022
Technology
0
170
Synthesizing Human Images in SIGGRAPH Asia 2021
SIGGRAPH Asia 2021の「Synthesizing Human Images」セッションに採択された5本の論文を紹介します.
Udon
February 27, 2022
Tweet
Share
More Decks by Udon
See All by Udon
MIRU2024_招待講演_RALF_in_CVPR2024
udonda
1
350
[CVPR24 Oral] Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation
udonda
0
300
Survey of Image Editing with GANs in SIGGRAPH'21
udonda
2
870
Network-to-Network Translation with Conditional Invertible Neural Networks
udonda
1
260
DARTS: Differentiable Architecture Search
udonda
0
120
Other Decks in Technology
See All in Technology
[IBM TechXchange Dojo]Watson Discoveryとwatsonx.aiでRAGを実現!事例のご紹介+座学②
siyuanzh09
0
110
My small contributions - Fujiwara Tech Conference 2025
ijin
0
1.5k
2025年に挑戦したいこと
molmolken
0
160
re:Invent2024 KeynoteのAmazon Q Developer考察
yusukeshimizu
1
150
シフトライトなテスト活動を適切に行うことで、無理な開発をせず、過剰にテストせず、顧客をビックリさせないプロダクトを作り上げているお話 #RSGT2025 / Shift Right
nihonbuson
3
2.2k
データ基盤におけるIaCの重要性とその運用
mtpooh
4
530
AWSの生成AIサービス Amazon Bedrock入門!(2025年1月版)
minorun365
PRO
7
470
RubyでKubernetesプログラミング
sat
PRO
4
160
Evolving Architecture
rainerhahnekamp
3
260
【Oracle Cloud ウェビナー】2025年のセキュリティ脅威を読み解く:リスクに備えるためのレジリエンスとデータ保護
oracle4engineer
PRO
1
100
あなたの人生も変わるかも?AWS認定2つで始まったウソみたいな話
iwamot
3
860
「隙間家具OSS」に至る道/Fujiwara Tech Conference 2025
fujiwara3
7
6.5k
Featured
See All Featured
Designing Experiences People Love
moore
139
23k
Thoughts on Productivity
jonyablonski
68
4.4k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
Done Done
chrislema
182
16k
VelocityConf: Rendering Performance Case Studies
addyosmani
327
24k
Automating Front-end Workflow
addyosmani
1366
200k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
160
15k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
870
Faster Mobile Websites
deanohume
305
30k
For a Future-Friendly Web
brad_frost
176
9.5k
Documentation Writing (for coders)
carmenintech
67
4.5k
Unsuck your backbone
ammeep
669
57k
Transcript
%BJDIJ)PSJUBൃද 4*((3"1)"TJB Synthesizing Human Images Session
୭ʁ 2
Synthesizing Human Images Session • URL: https://sa2021.siggraph.org/jp/attend/technical-papers/8/session/73 • 5ຊͷจ͕࠾ •
Barbershop • EyelashNet • Neural Actor • Pose with Style • SketchHairSalon 3
4
Barbershop ઃఆ — GAN inversion-based hair editing 5 Face identity
Generated image Hair color condition Hair texture condition Hair shape condition
• ͱإͷؒͷϒϨϯυΞʔςΟϑΝΫτΛੜͤ͡͞ͳ͍ੜ Barbershop ݁Ռ 6
Barbershop ख๏ 7 ͷલΛ” ” W+ F ͷޙΛ” ” W+
S C = (F, S) Face Hair ೖྗ ࠶ߏ Swap S ֤ೖྗ݅ ͷద༻ Blend ݟͨͷ࠷దԽ Face Identity Hair style
Barbershop ੍ݶ 8 • ᶃϚεΫ͕ͳ͍෦͋·Γ៉ྷʹ ͳΒͳ͍ • ᶄᶆϐΞεͷΑ͏ͳαϯϓϧ ແཧ •
ᶅᶇإΛःΔΑ͏ͳੜແཧ
9
EyelashNet ಈػ 10 ·ͭ͛ͷ3D࠶ߏࠔ ʢमਖ਼ʹ5࣌ؒఔඞཁʣ ·ͭ͛ͷMattingΛߦ͍ আڈ͔ͯ͠Βͷ3D࠶ߏ៉ྷʹͰ͖Δ with ·ͭ͛ w/o
·ͭ͛
EyelashNet ·ͭ͛σʔληοτ࡞ͷ 11 • ·ͭ͛άϦʔϯόοΫࡱӨͷΑ͏ͳํ๏ͰࡱӨͰ͖ͳ͍ • എܠʹͰͳ͘ɼલܠʹʢ·ͭ͛ʹܬޫృྉΛృͬͯࡱӨʣ
EyelashNet ·ͭ͛σʔληοτ࡞ͷ 12 • 2ຕͷࡱӨͷؒʹਓಈ͍ͯ͠·͏ͷͰ…ʁʁ • Optical flowͰҐஔ߹Θͤ XPҐஔ߹Θͤ XҐஔ߹Θͤ
EyelashNet ݁Ռ 13
14
Neural Actor ֓ཁ • ҙͷࢹɾ੍ޚՄೳͳϙʔζͰͷߴ࣭ͳਓؒ߹ͷͨΊͷख๏ • ϙʔζ<->ඪ४ۭؒͷมΛֶश 15
16 Neural Actor ܇࿅
NeuralActor ৽نࢹ߹࣮ݧ 17 ఆྔൺֱ ʢFID͕ۃʹྑ͍; γʔέϯεͰݟͨ࣌ʹ༏ΕΔʣ ఆੑൺֱ
18
Pose with Style ֓ཁ 19 • UVϚοϓ͕݅ͳStyleGAN2ʹΑΔશը૾ੜ ೖྗ ग़ྗ ਓੜ
Ծࢼண ೖྗ ग़ྗ
Pose with Style ܇࿅ 20 Ґஔ߹Θͤ 5BSHFUDPPSE HFOFSBUPS
Pose with Style ࣮ݧ — vs. Img-to-imgมϞσϧͱͷൺֱ 21 • ߴप៉ྷʹ
ੜ • ͷ༷ • إͷৄࡉ
Pose with Style ࣮ݧ — vs. StyleGAN-basedϞσϧͱͷൺֱ 22 • StylePoseGAN[Liu+
arXiv21] • Pose with StyleͷUVϚοϓʹର͢ ΔΛ΄ͱΜͲແͨ͘͠Α͏ͳ ख๏ • UVϚοϓΛ࠷େݶར༻͢Εߴ࣭
23
SketchHairSalon σʔληοτ࡞ 24 ೖྗ soft mask ࣗಈੜ खಈ •
soft maskMattingख๏Ͱ ਪ • ࣗಈੜͰฤΈࠐΈͳͲΛ දݱͰ͖ͳ͍ • खಈσʔληοτ͕ඞਢ
SketchHairSalon σʔληοτ࡞ 25 • ਪ࣌ʹ{ฤΈࠐΈ, ςΫενϟ}Λॻ͔ͤΔͷඇৗʹ໘͍͘͞ͷͰ…? • ύϥϝτϦοΫͳදݱؔΛఏҊ ฤΈࠐΈ ඇฤΈࠐΈ
SketchHairSalon ख๏ 26
SketchHairSalon ࣮ݧ 27
SketchHairSalon ੍ݶ 28 • Ԟߦ͖͕ඞཁͳܕݫ͍͠ • ແݶໟଋܕϑϥοτ ͳੜ • רࢴֶशαϯϓϧͱಉ͡
ੜ • Ԟߦ͖ߟྀͨ͠ੜͰղܾ(?)
·ͱΊ • ਓυϝΠϯͷΛѻ͏5ຊͷจΛհ • ฤू • Animatable NeRF • ·ͭ͛
• શੜ • ݻ༗ͷΛͲ͏ղܾ͢Δ͔ʁΛ͔ͳΓ۩ମతͳΞϓϩʔνͰղܾ͍ͯ͠Δ จ͕ଟ͔ͬͨ 29 Synthesizing Human Images Session