Pure 3×3 Convolutions for Image‑Generation Diffusion Models: The DiC Approach

The paper introduces DiC, a fully convolutional diffusion model that rethinks 3×3 convolutions, adds sparse skip connections, stage‑specific embeddings and conditional gating, and demonstrates superior FID/IS scores and faster inference compared to diffusion Transformers across multiple scales.

AIconvolutional networksdiffusion models

0 likes · 19 min read

Pure 3×3 Convolutions for Image‑Generation Diffusion Models: The DiC Approach