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
Vision Proで広告フリーな世界を実現したい
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
Shuhei Shitamori
December 12, 2024
Programming
250
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Vision Proで広告フリーな世界を実現したい
MIERUNE BBQ #14発表資料
Shuhei Shitamori
December 12, 2024
More Decks by Shuhei Shitamori
See All by Shuhei Shitamori
Photography is Dead?
shitamori1272
1
94
Vision Proで実現する 『ながら運動』健康促進術
shitamori1272
0
150
時差×英語×リモートでの コミュニケーション術
shitamori1272
0
87
写真はもう信用できない?フェイク検出から来歴証明へ
shitamori1272
1
87
Apple SharePlayで 非対称クロスプレイ チャレンジ (SharePlay使ってみた編)
shitamori1272
0
190
Foundation Models触ってみた - iPhone Dev Sapporo — WWDC25 Recap
shitamori1272
0
130
Wallet API, Verifier APIで実現するIDカード on iPhoneの世界
shitamori1272
1
3.6k
Other Decks in Programming
See All in Programming
Cloudflare is Agents
chimame
0
170
ソフトウェア設計に溶けるインフラ ― AWS CDK のインフラ認識論
konokenj
3
790
PHP に部分適用が来るぞ!……ところで何それ?おいしいの? #phpcon / phpcon-2026
shogogg
0
660
VibeCodingからAgenticWorkflowへ
starfish719
0
500
Google Apps Script で Ruby を動かす
kawahara
0
240
自動化したのに回らない テスト運用の壁―AI時代の品質責任と生産性
mfunaki
0
220
「寝てても仕事が進む」Claude Codeで組む第二の脳
tomoyafujita2016
0
330
GDG Korea Android: 2026 I/O Extended ~ What's new in Android development tools
pluu
0
220
What's New in Android 2026
veronikapj
0
260
ソフトウェアエンジニアにとっての生成AI - 特性を知って使い倒す / generative ai for software enginner
kishida
5
1.6k
Built Our Own Background Agent at LayerX
layerx
PRO
10
5.5k
Android CLI
fornewid
0
220
Featured
See All Featured
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
1
390
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
120
120k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
inesmontani
PRO
3
2.3k
Test your architecture with Archunit
thirion
1
2.3k
Navigating Weather and Climate Data
rabernat
0
480
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
490
KATA
mclloyd
PRO
35
15k
Redefining SEO in the New Era of Traffic Generation
szymonslowik
1
390
Building Applications with DynamoDB
mza
96
7.2k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
23k
The SEO identity crisis: Don't let AI make you average
varn
0
530
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Transcript
Լɹपฏ 2024/11/20 Vision ProͰࠂϑϦʔͳੈքΛ ࣮ݱ͍ͨ͠ MIERUNE BBQ
Լ पฏ w ࠓͷ݄͔Βࡳຈࡏॅ ग़Γ w Χφμͷσδλϧ*%ελʔτΞοϓͰJ04ΤϯδχΞ w 7JTJPO1SPങͬͨ
2 #MVFTLZ -JOLFEJO
XRͱ • Ծੈքͱݱ࣮ੈքͷΈ߹ΘͤʹΑͬͯ ৽ͨͳମݧΛੜΈग़ٕ͢ज़ͷ૯শ https://www.canon-its.co.jp/solution/mr/vr-ar-mr/
AR(֦ுݱ࣮)ͰͰ͖Δମݧ https://k-tai.watch.impress.co.jp/docs/news/1203694.html
ใྔ͕ଟ͍ͱετϨε • ใྔ͕ଟ͍ͱετϨεΛײ͍͢͡ • λεΫύϑΥʔϚϯεʹӨڹ • ใΛݮΒͨ͢ΊͷऔΓΈॏཁ
Diminished Reality(ݮଛݱ࣮) • ARͱରʹ࣮ࡍʹଘࡏ͢ΔͷΛϦΞϧλΠϜͰݟ͑ͳ͘͢Δٕज़ • ΠϠϗϯͷϊΠζΩϟϯηϦϯάͷࢹ֮όʔδϣϯ https://solution.itage.jp/2021/12/16/16738/
Vision ProͰDRΛͬͯΈΔ • ֗த͔ΒࠂுΓࢴΛফͯ͠ೝෛՙͷ͍ੈքΛ࣮ݱ͍ͨ͠
Vision Proͱ • Apple͕2023ʹൢച։࢝ͨ͠MRϔουηοτ • MacBookͱಉͷM2 νοϓࡌ • ߴղ૾ͷө૾ •
ϓϥΠόγʔΛྀͨ͠ମݧઃܭ
ࠂDRʹඞཁͳٕज़ Vision Proͷಛٕज़ཁ݅ʹϚον͍ͯ͠Δʂ • 1. ࢹ֮ใ(Χϝϥ)͔Βࠂͷݕग़ • Vision ProʹߴੑೳͳΧϝϥ͕ࡌ͞ΕͯΔ •
2. ࠂΛফͨ͢Ίͷഎܠը૾Λੜ • Vision ProʹAIΛಈ͔ͨ͢Ίͷߴੑೳͳνοϓ͕ࡌ͞ΕͯΔ • 3. ੜͨ͠ը૾ΛࠂʹॏͶͯදࣔ • Vision ProʹԾମΛۭؒʹஔͰ͖Δ
ࠂDRʹඞཁͳٕज़ Vision Proͷಛٕज़ཁ݅ʹϚον͍ͯ͠Δʂ͠ͳ͍… • 1. ࢹ֮ใ(Χϝϥ)͔Βࠂͷݕग़ • Vision ProʹߴੑೳͳΧϝϥ͕ࡌ͞ΕͯΔ͕ɺΧϝϥө૾ʹΞΫηεͰ͖ͳ͍ •
2. ࠂΛফͨ͢Ίͷഎܠը૾Λੜ • Vision ProʹAIΛಈ͔ͨ͢Ίͷߴੑೳͳνοϓ͕ࡌ͞ΕͯΔ͕ɺAI༻ΤϯδϯʹΞΫηεͰ͖ͳ͍ • 3. ੜͨ͠ը૾ΛࠂʹॏͶͯදࣔ • Vision ProʹԾମΛۭؒʹஔͰ͖Δ
ࠓճͷॲཧϑϩʔ • PCͰࣄલʹʮݕ͍ͨ͠ࠂʯͱʮॏͶ͍ͨഎܠը૾ͷੜʯΛΔ • Vision Proʮੜͨ͠ը૾ΛࠂʹॏͶͯදࣔʯ͚ͩ • ࢹ֮ใ(Χϝϥ)͔Β ࠂͷݕग़ 1.
ࠂΛࡱӨͯ͠σʔληοτ࡞ 2. ը૾͔ΒࠂྖҬΛݕग़ 3. ը૾ੜ༻ʹྖҬΛܗ ࠂΛফͨ͢Ίͷ എܠը૾ͷੜ 1. ࠂʹସΘΔഎܠը૾Λੜ 2. Vision Pro༻ʹը૾Λܗ ੜͨ͠ը૾Λ ࠂʹॏͶͯදࣔ 1. Vision Pro༻ͷΞϓϦΛ࡞ PCͰࣄલʹ AVPͰϦΞϧλΠϜʹ
ࢹ֮ใ(Χϝϥ)͔Βࠂͷݕग़ ࠂΛࡱӨͯ͠σʔληοτ࡞ • ԼమӺʹܝࡌ͞ΕͨࠂுΓࢴΛΧϝϥͰࡱӨ
ࢹ֮ใ(Χϝϥ)͔Βࠂͷݕग़ ը૾͔ΒࠂྖҬΛݕग़ • ը૾͔ΒҙͷΦϒδΣΫτΛݕग़Ͱ͖Δ Segmented Anything Model(SAM)ϕʔεͷϞσϧΛར༻ • prompt=“Advertisement”Ͱ֘͢ΔྖҬΛࣗಈͰݕग़ ”Advertisement”
https://github.com/hustvl/EVF-SAM
ࢹ֮ใ(Χϝϥ)͔Βࠂͷݕग़ ྖҬݕग़݁Ռͷܗ • ΪβΪβ݀ݕग़ྖҬͱͯ͠ෆਖ਼֬ͳͷͰ࢛֯ܗͱͯ͠ܗ • ܗޙͷը૾Λॏը૾ੜͷϚεΫͱͯ͠ར༻
ࠂΛফͨ͢Ίͷഎܠը૾ͷੜ ݕग़ྖҬΛੜAIͰ࠶ඳը • ը૾෮ݩʹಛԽͨ͠stable-di ff usionϞσϧͰϚεΫྖҬΛ࠶ੜ ޭ ύλʔϯ ࣦഊ ύλʔϯ
https://huggingface.co/stabilityai/stable-di ff usion-2-inpainting
ࠂΛফͨ͢Ίͷഎܠը૾ͷੜ Vision ProͰ͏σʔληοτΛ࡞ • Vision ProͰར༻͢Δը૾σʔληοτΛ࡞ • ݕग़༻ͷReference, ॏ༻ͷGeneratedΛ࡞ Reference
Generated
ੜͨ͠ը૾ΛࠂʹॏͶͯදࣔ Vision ProΞϓϦͷ࡞ • Reference ImageΛݕग़ͨ͠Β Generated ImageΛಉ͡Ґஔʹදࣔͤ͞ΔγϯϓϧͳΞϓϦ Reference ൃݟʂ
Generated ࠂ্ʹ ॏͶͯදࣔʂ
͍͟ɺӺߏͰ࣮ݧ ͦͷ1
͍͟ɺӺߏͰ࣮ݧ ͦͷ2
݁Ռ • Reference ImageΛ͖ͪΜͱݕग़ͯ͠Generated ImageΛॏදࣔͰ͖ͨ • ҰํͰ • ࠂʹेʹ͔ۙͮͳ͍ͱVision Pro͕ReferenceΛݕ͠ͳ͍
• Generated Imageʹมͳͷ͕ೖΓɺʮফ͢ʯ͜ͱ͕Ͱ͖ͳ͍࣌͋ͬͨ
ࠓޙվળ͢ΔͳΒ • ेʹࠂʹ͔ۙͮͳ͍ͱVision Pro͕ReferenceΛݕ͠ͳ͍ -> ͋Β͔͡Ί্ۭؒʹGenerated ImageΛஔ͓͚ͯ͠ ReferenceͷݕΛඞཁͱ͠ͳ͍͔ʁ • Generated
Imageʹมͳͷ͕ೖΓɺʮফ͢ʯ͜ͱ͕Ͱ͖ͳ͍࣌͋ͬͨ -> SAMʹΑΔࠂྖҬݕग़ͷਫ਼͕ෆेͩͬͨͷͰɺଞͷख๏ݕ౼ -> Generated ImageΛੜ͢Δࡍʹ”น”ͱ໌ࣔͯ͠ྑ͔͔ͬͨ