TF-PRDiT uses a frozen 3D diffusion transformer prior with task-specific forward operators and predictor-corrector sampling to solve X-ray-to-CT reconstruction and other volumetric inverse problems without any retraining.
arXiv preprint arXiv:2310.17167 (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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
citing papers explorer
-
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
TF-PRDiT uses a frozen 3D diffusion transformer prior with task-specific forward operators and predictor-corrector sampling to solve X-ray-to-CT reconstruction and other volumetric inverse problems without any retraining.
-
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