Unified Multi-plane Autoregressive Diffusion for 3D Multi-contrast MRI Synthesis
We propose a unified Multi-Plane Autoregressive Diffusion (MPAD), a latent diffusion framework that achieves full-volume 3D synthesis using efficient plane-wise 2D operations while preserving volumetric coherence.
ProofPaper ↗
Key points
- Acquiring a complete set of magnetic resonance imaging (MRI) contrasts is time-intensive and uncomfortable for patients, despite the diagnostic value of multi-contrast imaging.
- A 3D autoencoder first compresses MRI scans into an isotropic 3D la- tent representation.
- A 2D diffusion model is then trained to reconstruct masked latent slices of the target contrast, conditioned on both source- contrast slices and unmasked target-contrast slices.
- During inference, we introduce plane-wise autoregressive synthesis with inter-plane priors.
Sources (1)
- [1]Unified Multi-plane Autoregressive Diffusion for 3D Multi-contrast MRI SynthesisarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 03:31 AM
We propose a unified Multi-Plane Autoregressive Diffusion (MPAD), a latent diffusion framework that achieves full-volume 3D synthesis using efficient plane-wise 2D operations while preserving volumetric coherence.
Acquiring a complete set of magnetic resonance imaging (MRI) contrasts is time-intensive and uncomfortable for patients, despite the diagnostic value of multi-contrast imaging.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 7, 2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
- Oct 6, 2026Learning Transition Kernels of Jump-Diffusion Processes with Conditional Diffusion Models
- Oct 6, 2026SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation
- Oct 6, 2026Disentangling Dual Image References in Frequency Aware Diffusion Models for Personalized Generation
- Oct 6, 2026Uniform Discrete Diffusion Models are Minimax Optimal for Estimating Distributions with Small Effective Support Size
- Aug 10, 2026vllm-project/vllm v0.27.0