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
400
[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
Claude CodeでKiroの仕様駆動開発を実現させるには...
gotalab555
3
1.1k
【OptimizationNight】数理最適化のラストワンマイルとしてのUIUX
brainpadpr
2
510
MCP認可の現在地と自律型エージェント対応に向けた課題 / MCP Authorization Today and Challenges to Support Autonomous Agents
yokawasa
5
2.4k
Cloud WANの基礎から応用~少しだけDeep Dive~
masakiokuda
3
110
JAWS-UG のイベントで使うハンズオンシナリオを Amazon Q Developer for CLI で作ってみた話
kazzpapa3
0
100
Foundation Model × VisionKit で実現するローカル OCR
sansantech
PRO
1
400
Eval-Centric AI: Agent 開発におけるベストプラクティスの探求
asei
0
140
Amazon Inspector コードセキュリティで手軽に実現するシフトレフト
maimyyym
0
120
Google Agentspaceを実際に導入した効果と今後の展望
mixi_engineers
PRO
3
750
[kickflow]20250319_少人数チームでのAutify活用
otouhujej
0
110
AI関数が早くなったので試してみよう
kumakura
0
320
LLM 機能を支える Langfuse / ClickHouse のサーバレス化
yuu26
9
2.5k
Featured
See All Featured
Faster Mobile Websites
deanohume
309
31k
YesSQL, Process and Tooling at Scale
rocio
173
14k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.8k
Writing Fast Ruby
sferik
628
62k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
How to Ace a Technical Interview
jacobian
278
23k
Build your cross-platform service in a week with App Engine
jlugia
231
18k
Embracing the Ebb and Flow
colly
86
4.8k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3k
We Have a Design System, Now What?
morganepeng
53
7.7k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
760
How GitHub (no longer) Works
holman
314
140k
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