CVPR2017読み会

今回は、2017年7月に行われたConference on Computer Vision and Pattern Recognition 2017(CVPR2017)にて発表された研究2本を紹介します。

Transcript

1. $713ಡΈձ %XBOHP
   .FEJB
   7JMMBHF
   IJSPTIJCBL 
2. ঺հ͢Δ࿦จ %FFQ-FBSOJOHܥ   4UBDLFE
   (FOFSBUJWF
   "EWFSTBSJBM
   /FUXPSLT
   ڭࢣ͋ΓֶशλεΫͷதؒදݱΛੜ੒͢Δֶशͱɺ
   தؒදݱ͔Βը૾Λੜ੒͢ΔֶशΛಉ࣌ʹߦ͏ֶशख๏
    )JHI3FTPMVUJPO
   *NBHF
   *OQBJOUJOH
   VTJOH
   .VMUJ4DBMF
   /FVSBM
   1BUDI
   4ZOUIFTJT
   ࠷ॳʹ௿ղ૾౓ͳը૾Ͱम෮ͯ͠ߴղ૾౓ʹ֦େ͠ɺ
   पғͷը૾ͱ7((ಛ௃ྔ͕ۙ͘ͳΔΑ͏ʹೖྗը૾Λ࠷దԽ͢Δख๏ 'JHD 'JH
3. 4UBDLFE
   (FOFSBUJWF
   "EWFSTBSJBM
   /FUXPSLT  Xun Huang1 Yixuan Li2 Omid Poursaeed2 John Hopcroft1 Serge Belongie1,3 1Department of Computer Science, Cornell University 2School of Electrical and Computer Engineering, Cornell University 3Cornell Tech BEWFSTBSJBM
   MPTT &ODPEFS
   ʢ෼ྨλεΫΛࣄલֶशʣ (FOFSBUPS %JTDSJNJOBUPS 2OFUXPSL
   QSFEJDU
   [
   ʢ΄ͲΜͲ%ͱಉ͡ߏ଄ʣ DPOEJUJPOBM
   MPTT
   ʢ࠶ߏ੒ʣ FOUSPQZ
   MPTT
   ʢϊΠζ[Λແࢹ͠ͳ͍Α͏ʹʣ ߴ࣍ಛ௃ྔΛ࢖ͬͯΑΓ௿࣍ͳಛ௃ྔΛ࡞Δ 'JH
4. 4UBDLFE
   (FOFSBUJWF
   "EWFSTBSJBM
   /FUXPSLT  'JH 'JH
5. 4UBDLFE
   (FOFSBUJWF
   "EWFSTBSJBM
   /FUXPSLT 
6. )JHI3FTPMVUJPO
   *NBHF
   *OQBJOUJOH
   VTJOH
   .VMUJ4DBMF
   /FVSBM
   1BUDI
   4ZOUIFTJT  Chao Yang¡1, Xin Lu§2 , Zhe Lin†2 , Eli Shechtman‡2 , Oliver Wang∗2 , and Hao Lik1,3,4 1University of Southern California 2Adobe Research 3Pinscreen 4USC Institute for Creative Technologies ௿ղ૾౓ͳը૾Λ%FFQͰੜ੒͠ɺ
   म෮ՕॴͷपΓͷը૾ʹ߹͏Α͏ʹ/FVSBM
   1BUDI 'JH
7. )JHI3FTPMVUJPO
   *NBHF
   *OQBJOUJOH
   VTJOH
   .VMUJ4DBMF
   /FVSBM
   1BUDI
   4ZOUIFTJT  'JH 'JH