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
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Udon
February 27, 2022
Technology
0
190
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
430
[CVPR24 Oral] Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation
udonda
0
350
Survey of Image Editing with GANs in SIGGRAPH'21
udonda
2
910
Network-to-Network Translation with Conditional Invertible Neural Networks
udonda
1
330
DARTS: Differentiable Architecture Search
udonda
0
160
Other Decks in Technology
See All in Technology
10Xにおける品質保証活動の全体像と改善 #no_more_wait_for_test
nihonbuson
PRO
2
330
ClickHouseはどのように大規模データを活用したAIエージェントを全社展開しているのか
mikimatsumoto
0
270
Codex 5.3 と Opus 4.6 にコーポレートサイトを作らせてみた / Codex 5.3 vs Opus 4.6
ama_ch
0
210
Frontier Agents (Kiro autonomous agent / AWS Security Agent / AWS DevOps Agent) の紹介
msysh
3
190
今こそ学びたいKubernetesネットワーク ~CNIが繋ぐNWとプラットフォームの「フラッと」な対話
logica0419
5
460
会社紹介資料 / Sansan Company Profile
sansan33
PRO
15
400k
登壇駆動学習のすすめ — CfPのネタの見つけ方と書くときに意識していること
bicstone
3
130
AIエージェントに必要なのはデータではなく文脈だった/ai-agent-context-graph-mybest
jonnojun
1
250
配列に見る bash と zsh の違い
kazzpapa3
3
170
20260204_Midosuji_Tech
takuyay0ne
1
160
SREが向き合う大規模リアーキテクチャ 〜信頼性とアジリティの両立〜
zepprix
0
480
顧客の言葉を、そのまま信じない勇気
yamatai1212
1
360
Featured
See All Featured
Building the Perfect Custom Keyboard
takai
2
690
Rebuilding a faster, lazier Slack
samanthasiow
85
9.4k
The Art of Programming - Codeland 2020
erikaheidi
57
14k
Measuring & Analyzing Core Web Vitals
bluesmoon
9
760
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
140
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
The Spectacular Lies of Maps
axbom
PRO
1
530
Designing Powerful Visuals for Engaging Learning
tmiket
0
240
Between Models and Reality
mayunak
1
200
The Pragmatic Product Professional
lauravandoore
37
7.1k
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
190
Fireside Chat
paigeccino
41
3.8k
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