Metraipolis › archive › dc_90d249fd6e96
Spatial Lifting for Dense Prediction — arXiv:2610.00017
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00017
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:07:24.280Z
- SHA-256 of the archived text
df3f7c4068f761fb4f171ec6cc7bad91e2604650017b02390e0b3c056da1d055- Stable URL of this page
https://metraipolis.com/documento/dc_90d249fd6e96
How to cite
Spatial Lifting for Dense Prediction — arXiv:2610.00017 — arXiv (en), https://arxiv.org/abs/2610.00017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90d249fd6e96 (Metraipolis archive dc_90d249fd6e96, sha256 df3f7c4068f761fb4f171ec6cc7bad91e2604650017b02390e0b3c056da1d055)
BibTeX
@misc{dc90d249fd6e96,
title = {Spatial Lifting for Dense Prediction — arXiv:2610.00017},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00017},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90d249fd6e96; sha256 df3f7c4068f761fb4f171ec6cc7bad91e2604650017b02390e0b3c056da1d055},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a higher-dimensional space and subsequently processing them using networks designed for that higher dimension, such as a 3D U-Net. Counterintuitively, this dimensionality lifting allows us to achieve good performance on benchmark tasks compared to conventional approaches, while reducing inference costs and \textbf{drastically lowering the number of model parameters}. The SL framework produces intrinsically structured outputs along the lifted dimension. This emergent structure facilitates dense supervision during training and enables single-forward-pass self-consistency-based quality and uncertainty estimation at test time. Spatial Lifting introduces a simple and general modeling strategy that offers a promising path toward more efficient, accurate, and reliable deep networks for dense prediction tasks in vision.
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/2610.00017 — 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 2026-10-06T10:21:28.010Z 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).