Mufananidzo Colorization Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. Sei colorization yemufananidzo ichionekwa se 'ill-posed' dambudziko?
   • A single grayscale value inogona kuenderana neakawanda akasiyana mavara chaiwo
   • Mifananidzo yegreyscale haina ruzivo rwekushandisa zvachose
   • Mifananidzo yeruvara yakakurisa kuti isagadziriswa
   • Makamera haakwanise kurekodha greyscale zvakare
2. Mune yakakurumbira Lab ruvara nzvimbo nzira, iyo network inogashira sei sekuisa?
   • Iyo yakazara RGB mufananidzo
   • Chete L (kureruka) chiteshi
   • Chete dzvuku channel
   • Mepu yakadzama yechiitiko
3. Sei Zhang et al. furemu yerudzi rwekufanotaura sechikamu pamusoro peruvara 'mabhini' pane kudzoreredza zvakananga?
   • Nekuti kupatsanura ndicho chete chinhu neural network inogona kuita
   • Kuita kuti mifananidzo iite diki
   • Kuti udzivise avhareji yemavara akakodzera kuita akasvibira, ane desaturated mhedzisiro
   • Kubvisa kudiwa kwedata rekudzidziswa
4. Mamodheru anodzidza sei mavara zvinhu zvinofanira kunge pasina kuudzwa?
   • Iwo akarongwa nemaoko ane runyoro rwemavara echinhu chose
   • Vanofungidzira zvisina tsarukano nguva imwe neimwe
   • Vanoverenga metadata yemavara yakachengetwa mumafaira egreyscale
   • Ivo vanodzidza manhamba ekutanga kubva kumamirioni emavara emifananidzo akashandurwa kuita greyscale
5. Nderipi dambudziko rakakosha kana uchipenda vhidhiyo kwete mafoto ega?
   • Kuchengeta mavara achienderana pamafuremu kudzivirira kupenya
   • Mavhidhiyo haana greyscale shanduro
   • Ruvara harubviri kuwedzera kumifananidzo inofamba
   • Furemu imwe neimwe inofanira kuva nemuvara wakasiyana
6. Chii chinoita eemplar-based kana hint-based colorization inobvumira mushandisi kuita?
   • Shandura mifananidzo yemavara kuti idzokere ku grayscale chete
   • Tungamira zvinobuda uchishandisa referensi mifananidzo kana kudzvanya mavara emavara
   • Dzima iyo neural network zvachose
   • Shandura mufananidzo kune mumwe mutauro
7. In the CIE Lab setup described in the guide, which channels does the network predict?
   • The L lightness channel only
   • RGB red and green but not blue
   • The a and b chrominance channels
   • The image’s camera pose
8. Why can direct regression toward an average color produce dull colorization?
   • The model is forced to output only black
   • Regression removes the lightness channel
   • The network cannot use training examples
   • Several plausible colors for a gray pixel may average to a muted, less likely color