Machine learning

Difuzijski model

Difuzijski model je generativna metoda dubokog učenja, koju su 2020. godine predstavili Ho, Jain i Abbeel (DDPM), a koja uči proizvoditi visokokvalitetne slike, zvuk i molekularne strukture reverziranjem postupnog procesa šuma. Uvelike je zamijenila GAN-ove kao trenutačno najsuvremenije rješenje u generativnom modeliranju.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

+1 more

Izvori

  1. Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS. link
  2. Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. CVPR. link

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Denoising Diffusion Probabilistic Model (DDPM / Latent Diffusion). ScholarGate. https://scholargate.app/hr/deep-learning/diffusion-model

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateDiffusion Model (Denoising Diffusion Probabilistic Model (DDPM / Latent Diffusion)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/diffusion-model · Skup podataka: https://doi.org/10.5281/zenodo.20539026