Kediska Midabaynta Sawirka

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

1. Waa maxay sababta midabaynta sawirka loogu tixgaliyaa inay tahay dhibaato 'jilicsan'?
   • Hal qiime oo cawl ah ayaa u dhigmi kara midabo badan oo kala duwan
   • Sawirada cawlan haba yaraatee ma jiraan macluumaad la isticmaali karo
   • Sawirada midabku aad bay u weyn yihiin in la farsameeyo
   • Kamaradu hadda ma duubi karto cabbir cawl
2. Habka goobta midabka caanka ah ee Shaybaadhka, maxay shabakadu u heshaa gelinta ahaan?
   • Sawirka RGB oo buuxa
   • Kaliya kanaalka L (iftiin).
   • Kaliya kanaalka cas
   • Maab qoto dheer oo goobta ah
3. Waa maxay sababta Zhang et al. Saadaasha midabka qaabaysan sida kala soocida 'bins' midabka halkii ay ka ahaan lahayd dib u noqoshada tooska ah?
   • Sababtoo ah kala soocida ayaa ah waxa kaliya ee shabakadaha neerfaha ay sameyn karaan
   • Si sawirada looga dhigo kuwo yaryar
   • Si looga fogaado in celcelis ahaan midabada saxda ah noqdaan kuwo caajis ah, natiijooyin qallafsan
   • Si meesha looga saaro baahida xogta tababarka
4. Sidee bay moodooyinka u bartaan midabada walxaha ay tahay inay noqdaan iyada oo aan loo sheegin?
   • Waxa gacanta lagu habeeyay liiska midabka shay kasta
   • Waxay u maleeyaan si aan kala sooc lahayn mar kasta
   • Waxay akhriyaan xogta badan ee midabka ee ku kaydsan faylalka cawl
   • Waxay ka bartaan xisaabaad hore malaayiin sawiro midab ah oo loo beddelay miisaan
5. Waa maxay caqabadda muhiimka ah marka la midabaynayo muuqaalka halkii sawir keliya laga samayn lahaa?
   • Ka ilaalinta midabada si joogto ah oo dhan fareemka si looga fogaado liidashada
   • Fiidiyowyadu ma laha nooc cawlan
   • Midabku macquul maaha in lagu daro sawirada dhaqaaqa
   • Jir kastaa waa inuu noqdaa midab kala duwan
6. Muxuu midabayn ku salaysan tusaale-ku-salaysan ama tilmaan-ku-salaysan u ogolaanaya isticmaaluhu?
   • U beddelo sawirada midabka midab cawl oo keliya
   • Ku hag wax soo saarka adigoo isticmaalaya sawirro tixraac ah ama tilmaamo midab la gujiyay
   • Dami shabakada neerfaha gabi ahaanba
   • U tarjun sawirka luuqad kale
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