Agba nke onyonyo
Ịchacha ihe onyonyo na-eji AI gbakwunye ezigbo agba na foto na ihe nkiri ojii na ọcha.
Nchịkọta
It matters because it brings historical archives to life and restores faded or grayscale imagery without manual painting.
Ime miri emi
Ịme agba bụ isi nsogbu na-adịghị mma: otu pikselụ isi awọ nwere ike ịbụ ọtụtụ agba, ebe ọ bụ naanị nchapụta anaghị ekpuchi hue. Usoro ọgbara ọhụrụ na-ewere ya dị ka amụma, na-amụta site na ọtụtụ nde foto agba ndị ejiri aka mee ka ọ bụrụ isi awọ. Netwọk mgbanwe ma ọ bụ ihe ntụgharị na-ahụ naanị ọwa ọkụ wee buru amụma ọwa agba na-efu efu, na-adịkarị na oghere agba CIE Lab ebe L na-ejide nchapụta yana a/b jigide agba. N'ihi na ahihia na-abụkarị akwụkwọ ndụ akwụkwọ ndụ na mbara igwe na-acha anụnụ anụnụ, ihe nlereanya ahụ na-amụta ụzọ mgbakọ na mwepụ siri ike. Ọrụ akara ala nke Zhang et al. (2016) kpụrụ ya dị ka nkewa agba bọket iji zere ịsachapụ, desaturated averages. Mgbasa ọhụrụ na ụzọ dabere na ihe nlere anya na-ahapụ ndị ọrụ na-eduzi agba na nkọwa ma ọ bụ onyonyo ntụaka maka njikwa ka mma.
Nghọta nka nka
Ọtụtụ usoro na-arụ ọrụ na Lab ohere: netwọk na-enweta naanị L (ìhè) ọwa na mmepụta na a na b chrominance ọwa, nke na-recombined na mbụ L. N'imeso agba amụma dị ka a nkewa n'elu quantized bins, kama regressing kpọmkwem ụkpụrụ, na-egbochi ihe nlereanya si averaging multiple irè agba n'ime a dull agba aja aja-agba ntụ, na-arụpụta obi ike na-arụpụta ihe ọzọ vivid.
Mmetụta atụmatụ
Ọsọ na ọnụ ọgụgụ
Visual AI nwere ike megharịa nyocha, nchọpụta na mkpado ọrụ n'ọtụtụ.
Mee nhọrọ
Otu ndị na-emepụta ihe nwere ike imepụta echiche ngwa ngwa site na ngbanwe akwụkwọ ntuziaka ole na ole.
Team na usoro ọrụ
Ọrụ nwere ike iji onyonyo na akara vidiyo siri ike ịhazi.
Ọdịnihu nke agba agba onyonyo
Colorization na-aga n'ihu na ngwa mmekọrịta, enwere ike ịchịkwa ebe onye ọrụ na-pịa agba ngosi na ihe nlereanya na-agbasa ya mgbe niile. Ụdị mgbasa ozi na mkpali asụsụ ("mee ka uwe ahụ na-acha uhie uhie") na-agbakwunye njikwa ntụgharị uche, ebe netwọk ndị maara nwa oge na-agbacha ihe nkiri niile na-enweghị atụgharị na etiti. Na-atụ anya njikọ siri ike na pipeline mweghachi nke na-ekwupụta n'otu oge, na-agbago ma na-acha agba, gbakwunyere nchebe siri ike na-egosi na agba bụ echiche AI na-eche kama ịbụ eziokwu akụkọ ihe mere eme.
Mmejuputa n'ezie n'ụwa
Na-eweghachi ụdị agba agba nke oge Agha Ụwa nke mere na narị afọ nke 19 maka ụlọ ngosi ihe mgbe ochie na akwụkwọ akụkọ.
Na-eweta ihe nkiri ojii na-acha ọcha na ihe nkiri TV na agba maka mwepụtagharị ọzọ
Ngwa foto ezinụlọ (dị ka MyHeritage na Google Foto) ndị na-ese foto ochie na-acha akpaaka.
Ịmepụta nyocha ahụike ma ọ bụ sayensị isi awọ iji mee ka arụ ọrụ pụta ìhè ma melite nkọwa ọhụụ
Ihe ize ndụ & okporo ụzọ nche
Ikike onyonyo na nkwenye nwere ike bụrụ ihe egwu dị n'iwu ma ọ bụrụ na edoghị anya.
Ọrụ nlereanya nwere ike ịdịgasị iche n'ofe ọkụ, igwe mmadụ, na gburugburu.
Enwere ike ghara ịhụ ihe dị mma ma ọ bụrụ na enyochaghị oke ntụkwasị obi.
Map mmejuputa
Kọwaa ụkpụrụ nnabata maka nkenke, icheta, na ụgwọ njehie.
Nwalee na data dabara na ọnọdụ mmepụta n'ezie.
Tinye nyocha mmadụ maka obere obi ike ma ọ bụ amụma mmetụta dị elu.
Sochie ihe nlere anya wee megharịa ka emechara mgbanwe igwefoto ma ọ bụ dataset.
Nọgide na-eme nchọpụta
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Image Colorization quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Ntuziaka na-esote
Nchịkọta onyonyo Semantic SPADE
Ajụjụ a na-ajụkarị
What is Image Colorization?
Ịchacha ihe onyonyo na-eji AI gbakwunye ezigbo agba na foto na ihe nkiri ojii na ọcha. Ọ dị mkpa n'ihi na ọ na-eme ka ihe ndekọ akụkọ ihe mere eme dị ndụ ma na-eweghachi onyonyo dara ada ma ọ bụ isi awọ na-enweghị eserese aka.
Kedu ihe kpatara eji ele agba agba onyonyo anya dị ka nsogbu 'adịghị mma'?
Icha ọkụ naanị anaghị ekpebi agba, yabụ otu pikselụ isi awọ nwere ike ịbụ ọbara ọbara, acha anụnụ anụnụ ma ọ bụ akwụkwọ ndụ akwụkwọ ndụ, na-eme ka azịza ya bụrụ ihe mgbagwoju anya.
N'ime usoro oghere oghere ụlọ nyocha ama ama, kedu ihe netwọk na-enweta dị ka ntinye?
Ihe oyiyi isi awọ bụ ọwa L; Ihe nlereanya ahụ na-ebu amụma ọwa agba a na b na-efu ma jiri L.
Gịnị mere Zhang et al. amụma agba agba dị ka nkewa n'elu 'bins' agba kama ịlaghachi azụ ozugbo?
Ịlaghachite otu uru na-eme ka ọ bụrụ nkezi ọtụtụ agba ndị nwere ike ime ka ọ bụrụ apịtị agba aja aja-isi awọ; Nkewa n'ime bins na-eme ka agba pụta ìhè.
Kedu ka ụdị si amụta ihe agba ihe kwesịrị ịbụ n'agwaghị ya?
Ọzụzụ na nnukwu dataset na-akụzi ihe nlereanya na ahịhịa na-abụkarị akwụkwọ ndụ akwụkwọ ndụ, igwe na-acha anụnụ anụnụ, na ụda akpụkpọ ahụ na-adaba n'ụdị ụfọdụ.
Kedu ihe bụ isi ihe ịma aka mgbe ị na-agbazi vidiyo kama ịbụ otu foto?
Ọ bụrụ na okpokolo agba nke ọ bụla nwere agba na-adabereghị na ya, otu ihe ahụ nwere ike ịgbanwe agba n'etiti okpokolo agba, na-ebute flicker na-adọpụ uche; ụdị oge na-elebara nke a anya.