Metraipolis › archive › dc_c64f9fc19b4e
VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis — arXiv:2608.04557
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04557
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:47:57.851Z
- SHA-256 of the archived text
6e265b52c929438a8bc14cde2afa23000c86e29a65fd386a8039bef05f67abbd- Stable URL of this page
https://metraipolis.com/documento/dc_c64f9fc19b4e
How to cite
VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis — arXiv:2608.04557 — arXiv (en), https://arxiv.org/abs/2608.04557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c64f9fc19b4e (Metraipolis archive dc_c64f9fc19b4e, sha256 6e265b52c929438a8bc14cde2afa23000c86e29a65fd386a8039bef05f67abbd)
BibTeX
@misc{dcc64f9fc19b4e,
title = {VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis — arXiv:2608.04557},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04557},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c64f9fc19b4e; sha256 6e265b52c929438a8bc14cde2afa23000c86e29a65fd386a8039bef05f67abbd},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-fidelity 3D MRI synthesis requires both globally coherent anatomy and fine-grained voxel-level detail. Although latent diffusion makes volumetric generation tractable, its image autoencoder introduces a reconstruction bottleneck that can limit the fine detail recoverable in the final volume. We present VoxStruct3D, a voxel-space flow-matching framework that directly models full-resolution MRI volumes using a clean-data prediction objective. Its Volumetric Voxel Generator (VVG) combines factorized 3D patch embedding with overlapping upsampling, time-modulated residual refinement, and skip fusion, enabling neighboring tokens to jointly reconstruct shared voxel regions and suppress patch-boundary artifacts. To complement direct voxel-space modeling with an explicit anatomical prior, we further introduce a Structure-First, Image-Follows (SFIF) strategy. A frozen pretrained 3D medical encoder and a StructVAE extract compact structure tokens that preserve dominant anatomy, while a structure-leading schedule keeps their trajectory ahead of the image trajectory. Patch-Aligned RoPE spatially aligns the unequal token grids, and asymmetric attention enforces one-way guidance from structure to image. Experiments on pathological and healthy T1-weighted brain MRI datasets show that VoxStruct3D achieves the strongest overall performance across feature-distribution alignment, sample diversity, and perceptual quality, producing anatomically coherent and visually realistic volumes. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04557 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:37:40.681Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).