SciFusion is a multimodal framework that uses a latent diffusion backbone to generate unified 3D scientific images. It introduces a compositional conditioning scheme that separates each modality into domain, object, and contrast representations, allowing knowledge transfer and zero‑shot synthesis of unseen compositions. The model also incorporates physics‑informed objectives specific to MRI, CT, and electron microscopy to ensure generated images respect modality‑dependent image formation processes, and demonstrates improved fidelity and cross‑domain generalization across 15 imaging modalities.
Existing 3D generative approaches are typically developed for individual imaging modalities, requiring substantial modality-specific data and limiting their ability to exploit shared structure across...
arXiv:2608. 08135v1 Announce Type: cross Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitations: methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task.
arXiv:2606. 17989v1 Announce Type: cross Abstract: Multi-contrast magnetic resonance imaging (MRI) provides complementary information for clinical diagnosis.
arXiv:2602. 18400v3 Announce Type: replace-cross Abstract: Missing data problems, such as missing modalities in multi-modal brain MRI and missing slices in cardiac MRI, pose significant challenges in clinical practice.
arXiv:2610.09253v1 Announce Type: new Abstract: Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric info...
Generating CT volumes from MRI and CBCT can improve treatment planning in adaptive radiotherapy while avoiding additional radiation exposure. However, direct regression of CT intensities is challenged by the inherently high dynamic range and long-tailed distributions, thereby averaging out sparse yet clinically important structures.
Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information. We propose PhyDiCT, a training-free fram...
arXiv:2610.09376v1 Announce Type: new Abstract: Acquiring a complete set of magnetic resonance imaging (MRI) contrasts is time-intensive and uncomfortable for patients, despite the diagnostic value o...
UltraDiff is a new framework for high‑resolution image generation with Latent Diffusion Models that tackles the trade‑off between computational cost and fidelity caused by latent compression. It jointly learns latent diffusion and then distills a marginal score using a dual‑branch DiT called MixTeacher, which models both f8 and f32 distributions and resolves compressed‑space ambiguity with high‑fidelity priors. Vector‑field distillation in the native f32 space forces the student model to learn the teacher’s conditional expectation, filtering out compression artifacts and achieving f8‑level quality while retaining f32 efficiency—generating a 2K image in 6.2 seconds on a single A100 GPU, over 40× faster than the f8 baseline.
arXiv:2403. 18026v3 Announce Type: replace-cross Abstract: High-throughput imaging is often constrained by a trade-off between acquisition speed and image quality.
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
The paper presents a 3D foundation model for light sheet fluorescence microscopy (LSM) that is pretrained on a large curated set of 3D images from various organisms, stains, and imaging protocols. By jointly optimizing for masked reconstruction and image‑text alignment, the model learns transferable volumetric representations that dramatically reduce the need for annotated data. The pretrained backbone enables efficient few‑shot adaptation to downstream tasks such as segmentation, classification, and deblurring, consistently outperforming baselines according to standard metrics and expert evaluation.