Frequency-Time Diffusion with Neural Cellular Automata
원문 초록
Despite considerable success, large Denoising Diffusion Models (DDMs) with UNet backbone pose practical challenges, particularly on limited hardware and in processing gigapixel images. To address these limitations, we introduce two Neural Cellular Automata (NCA)-based DDMs: Diff-NCA and FourierDiff-NCA. Capitalizing on the local communication capabilities of NCA, Diff-NCA significantly reduces the parameter counts of NCA-based DDMs. Integrating Fourier-based diffusion enables global communication early in the diffusion process. This feature is particularly valuable in synthesizing complex images with important global features, such as the CelebA dataset. We demonstrate that even a 331k parameter Diff-NCA can generate 512x512 pathology slices, while FourierDiff-NCA (1.1m parameters) reaches a three times lower FID score of 43.86, compared to the four times bigger UNet (3.94m parameters) with a score of 128.2. Additionally, FourierDiff-NCA can perform diverse tasks such as super-resolution, out-of-distribution image synthesis, and inpainting without explicit training.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
Noise Conditional Variational Score Distillation
Grids Often Outperform Implicit Neural Representations
fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpainting
DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion
Exploring Diffusion with Test-Time Training on Efficient Image Restoration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.