A training-free global-local skipping strategy accelerates 3D diffusion-based PET denoising by over an order of magnitude while maintaining or improving image quality across multiple tracers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.
citing papers explorer
-
Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction
A training-free global-local skipping strategy accelerates 3D diffusion-based PET denoising by over an order of magnitude while maintaining or improving image quality across multiple tracers.
-
Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures
Profiling of Med-DDPM shows cuDNN kernels dominate training; TF32 Tensor Core activation and 3D channels-last layout reduce SM cycles up to 100x and raise Tensor Core utilization on A100 without quality loss.