PRDiT generates voxel-level 3D CT volumes via a local MLP patch denoiser for low-frequency structures and a memory-efficient global residual diffusion transformer for high-frequency details, outperforming HA-GAN, 3D LDM, and WDM-3D on LIDC-IDRI and RAD-ChestCT with lower FID, MMD, and Wasserstein sc
Paul Friedrich, Julia Wolleb, Florentin Bieder, Alicia Durrer, and Philippe C Cattin
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
PRDiT generates voxel-level 3D CT volumes via a local MLP patch denoiser for low-frequency structures and a memory-efficient global residual diffusion transformer for high-frequency details, outperforming HA-GAN, 3D LDM, and WDM-3D on LIDC-IDRI and RAD-ChestCT with lower FID, MMD, and Wasserstein sc