Metraipolis › archive › dc_4971811071fe
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation — arXiv:2610.02201
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02201
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:16:35.675Z
- SHA-256 of the archived text
e205cbb4a3af1bd0f214d9035df5060d8a67af000d7177bdec94f1eebd40c30a- Stable URL of this page
https://metraipolis.com/documento/dc_4971811071fe
How to cite
SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation — arXiv:2610.02201 — arXiv (en), https://arxiv.org/abs/2610.02201 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4971811071fe (Metraipolis archive dc_4971811071fe, sha256 e205cbb4a3af1bd0f214d9035df5060d8a67af000d7177bdec94f1eebd40c30a)
BibTeX
@misc{dc4971811071fe,
title = {SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation — arXiv:2610.02201},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02201},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4971811071fe; sha256 e205cbb4a3af1bd0f214d9035df5060d8a67af000d7177bdec94f1eebd40c30a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02201. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topological consistency for thin or highly connected shapes. We introduce SILSA, a topology-aware 3D generation framework that represents shapes with compact sliding-window slice latents. Instead of generating expensive voxel tokens, SILSA uses a fixed set of overlapping slices along the three canonical axes, where each token summarizes a local depth window to preserve cross-sectional continuity and support single-stage rectified-flow generation. A Slice VAE encodes oriented surface samples into multi-axis slice latents and reconstructs them with a sparse volumetric decoder, while a Volumetric Anchor Lattice coordinates directional slice streams through a shared 3D workspace. To preserve structural correctness, we introduce slice-level topology supervision that matches persistence diagrams and aligns Betti transitions across neighboring slices. Experiments show that SILSA improves structural fidelity while substantially reducing generation cost. SILSA improves PSNR by $8.7\%$, coverage by $5.96$ absolute points, and Betti error by $9.2\%$ over the strongest baseline, while using $70.0\%$ fewer tokens than the next-most compact baseline and over $98\%$ fewer tokens than sparse or hierarchical tokenizers, effectively reducing training memory by $40.4\%$ and inference time by $58.5\%$. Qualitative results further show improved preservation of thin structures, repeated components, and long-range connectivity. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.02201 — 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 2026-10-06T10:21:28.262Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).