diffusion models 23d image generation 1cross-attention 1CT reconstruction 1inverse problems 1medical imaging 1training-free methods 1triplane representation 1volumetric imaging 1
From the 2 of 6 linked papers with an AI index.
Showing eess.IVShow all
2 papers · 1 filter
eess.IV2026
TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion Model
Zhenkai Zhang, Krista A. Ehinger, Tom Drummond
The paper presents TCAM-Diff, a diffusion-based model that uses a triplane-aware cross‑attention mechanism and a decoder‑only autoencoder to efficiently generate high‑resolution 3D…
eess.IV2026
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
Zhenkai Zhang, Markus Hiller, Krista A. Ehinger +1
The paper introduces TF-PRDiT, a training‑free framework that uses a frozen 3D diffusion transformer prior to reconstruct CT volumes from sparse X‑ray projections, and can be appli…