SSII2023 [OS1] グラフィックデザインとマルチモーダル処理

⼭⼝光太（CyberAgent）

Transcript

1. グラフィックデザインと マルチモーダル処理 2023.6.14 ⼭⼝ 光太（CyberAgent）
2. CyberAgent AI Lab • ػցֶश • ίϯϐϡʔλϏδϣϯ • ίϯϐϡʔλάϥϑΟοΫε • ࣗવݴޠॲཧ • Ի੠৴߸ॲཧ • HCI / ϩϘοτ • ܭྔܦࡁֶ
3. ΞδΣϯμ 1. άϥϑΟοΫσβΠϯͷϞμϦςΟ 2. ࠷ۙͷऔΓ૊Έ
4. άϥϑΟοΫσβΠϯͷϞμϦςΟ 01
5. άϥϑΟοΫσβΠϯ • εϥΠυγϣʔɺιʔγϟϧϝσΟΞ౤ߘɺϙελʔɺ ಈը޿ࠂɺWebϖʔδ
6. άϥϑΟοΫσβΠϯ͸͍ΘΏΔը૾Ͱ͸ͳ͍ ϕΫλάϥϑΟοΫ ϥελը૾ Rendering σβΠφʔͷѻ͏΋ͷ σΟεϓϨΠʹөΔ΋ͷ
7. ϥελը૾ • JPEG, PNG, WebP • ݻఆղ૾౓ϐΫηϧɺυοτֆ • ͍ΘΏΔը૾ ϕΫλάϥϑΟοΫ • PDF, PPTX, Photoshop • ղ૾౓ඇґଘͷඳըࢦࣔ • ͍ΘΏΔυΩϡϝϯτ ϥελܗࣜͱϕΫλܗࣜ Typography Typography Typography
8. ঎ۀάϥϑΟοΫσβΠϯͷཁૉ • ͨ͘͞ΜͷϞμϦςΟɺςʔϒϧσʔλʹ͍ۙ ίϐʔ ண஍ϖʔδ Ωϟϯϖʔϯ άϥϑΟοΫ ϓϥοτϑΥʔϜ දࣔσόΠε ίϯςϯπ ίϯςΩετ ഔମ *1 ௌऺ
9. ϕΫλάϥϑΟοΫͷσʔλߏ଄ Canvas Image Text Text Text Text Canvas Image Text Text Text Text υΩϡϝϯτ , Ωϟϯόε ϨΠϠʔ Width, Height, Category, … Type, Position, Size, Appearance, Text, Pixels, …
10. ϨΠΞ΢τੜ੒ • ϨΠΞ΢τ͸(type, left, top, width, height)ͷϨΠϠʔλϓϧͷܥྻ • ϨΠΞ΢τੜ੒͸ϚϧνϞʔμϧͳܥྻੜ੒໰୊ʹؼண t1 x1 y1 w1 h1 t2 x2 y2 w2 h2 … Layer 1 Layer 2 Generator Canvas Layer 1 Layer 2
11. ςΩετͷٯϨϯμϦϯά • ϚϧνλεΫɾϚϧνϞʔμϧͳ༧ଌ Resolution: [1699, 1280] Location: [247, 1130, 748, 1280] Text: "WANT" Font: Barlow Semi Condensed ExtraBold Fill: RGB: [44, 34, 41] Border: Visible: True RGB: [217, 91, 97] Width: 2 Shadow: Visible: False Background: <pixels> ٯϨϯμϦϯά
12. N Inoue et al., LayoutDM: Discrete Diffusion Model for Controllable Layout Generation, CVPR 2023 N Inoue et al., Towards Flexible Multi-modal Document Models, CVPR 2023 ࠷ۙͷऔΓ૊Έ 02
13. LayoutDM[Ҫ্+] ɿϨΠΞ΢τੜ੒ • ཭ࢄ֦ࢄϞσϧʹΑΔϨΠΞ΢τੜ੒
14. ϨΠΞ΢τͷͨΊͷϚϧνϞʔμϧ཭ࢄදݱ • (type, left, top, width, height)ͷܥྻσʔλΛϞμϦςΟຖʹಠཱͯ͠཭ࢄදݱ • D3PM[J Austin 21]ʹΑΔ཭ࢄ֦ࢄੜ੒Ϟσϧͷద༻
15. ֤छϨΠΞ΢τੜ੒λεΫ
16. FlexDM[Ҫ্+] : σβΠφʔͷฤू޻ఔͷϞσϦϯά • ଟछଟ༷ͳϚϧνϞʔμϧɾϚϧνλεΫॲཧΛ͢ΔΤϯίʔμϞσϧ FlexDM Layout generation Texts filling Font & color styling Images filling Element filling … type: Text pos: (150, 30) size: (200, 90) text: Happy\nHolidays! image: font: color: Arial (210,220,100) - [MASK] [MASK] [NULL] type: Text pos: (150, 30) size: (200, 90) text: Happy\nHolidays! image: font: color: …
17. ϚεΫ෇͖ΦʔτΤϯίʔμͷϚϧνλεΫ׆༻ • ϚϧνϞʔμϧͳBERTతͳϞσϧ→ϚεΫ੾Γସ͑Ͱଟ༷ͳλεΫॲཧ Design tasks = = Masking patterns Font & color prediction Element filling BEST IN TOWN! CAR WASH Full service Type Position Img-emb. Text-emb. Color / font context [NULL] [MASK] 1 2 3 4 5 1 2 3 4 5 Type Position Img-emb. Text-emb. Color / font context [NULL] [MASK] 1 2 3 4 5 1 2 3 4 5
18. ग़ྗྫ Output Input Output Input Output Input ATTR prediction TXT prediction IMG prediction POS prediction Element filling Output Input Output (bbox.) Output (img.) Output (bbox.) Output (img.)
19. άϥϑΟοΫσβΠϯͱϚϧνϞʔμϧॲཧ • άϥϑΟοΫσβΠϯ͸ը૾ɺจࣈɺزԿ ഑ஔɺελΠϦϯάଐੑͳͲϚϧνϞʔμ ϧߏ଄σʔλ • γʔέϯεߏ଄ͷ׆༻Ͱ֤छλεΫͷఆࣜ Խ͕Մೳʹ