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
180
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
410
[CVPR24 Oral] Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation
udonda
0
340
Survey of Image Editing with GANs in SIGGRAPH'21
udonda
2
900
Network-to-Network Translation with Conditional Invertible Neural Networks
udonda
1
310
DARTS: Differentiable Architecture Search
udonda
0
150
Other Decks in Technology
See All in Technology
リセラー企業のテクサポ担当が考える、生成 AI 時代のトラブルシュート 2025
kazzpapa3
1
150
Simplifying Cloud Native app testing across environments with Dapr and Microcks
salaboy
0
130
OCI Network Firewall 概要
oracle4engineer
PRO
2
7.8k
後進育成のしくじり〜任せるスキルとリーダーシップの両立〜
matsu0228
7
3.2k
「使い方教えて」「事例教えて」じゃもう遅い! Microsoft 365 Copilot を触り倒そう!
taichinakamura
0
320
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
11
78k
AWS Top Engineer、浮いてませんか? / As an AWS Top Engineer, Are You Out of Place?
yuj1osm
2
210
生成AIとM5Stack / M5 Japan Tour 2025 Autumn 東京
you
PRO
0
240
LLM時代にデータエンジニアの役割はどう変わるか?
ikkimiyazaki
6
1.2k
『バイトル』CTOが語る! AIネイティブ世代と切り拓くモノづくり組織
dip_tech
PRO
1
110
10年の共創が示す、これからの開発者と企業の関係 ~ Crossroad
soracom
PRO
1
700
Escaping_the_Kraken_-_October_2025.pdf
mdalmijn
0
160
Featured
See All Featured
Why Our Code Smells
bkeepers
PRO
339
57k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.7k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.7k
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.7k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Designing for humans not robots
tammielis
254
26k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
GraphQLとの向き合い方2022年版
quramy
49
14k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.7k
Embracing the Ebb and Flow
colly
88
4.8k
Into the Great Unknown - MozCon
thekraken
40
2.1k
Unsuck your backbone
ammeep
671
58k
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