Metraipolis › archive › dc_c42e58869069
Soft-Argmax for the Projective Plane via the Veronese Embedding — arXiv:2609.00521
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00521
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:52:32.749Z
- SHA-256 of the archived text
3fe6733b898f9142cf41256d9ea218715dd44ea8d8ee999362a24e4fa2527a9b- Stable URL of this page
https://metraipolis.com/documento/dc_c42e58869069
How to cite
Soft-Argmax for the Projective Plane via the Veronese Embedding — arXiv:2609.00521 — arXiv (en), https://arxiv.org/abs/2609.00521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c42e58869069 (Metraipolis archive dc_c42e58869069, sha256 3fe6733b898f9142cf41256d9ea218715dd44ea8d8ee999362a24e4fa2527a9b)
BibTeX
@misc{dcc42e58869069,
title = {Soft-Argmax for the Projective Plane via the Veronese Embedding — arXiv:2609.00521},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00521},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c42e58869069; sha256 3fe6733b898f9142cf41256d9ea218715dd44ea8d8ee999362a24e4fa2527a9b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
From horizon detection to fibre structures in X-ray imaging, many vision tasks recover lines via peak detection in Hough space $H=S^1\times\mathbb{R}$, the domain of orientation-offset pairs $(\theta,\rho)$. Differentiable pipelines extract coordinates via \emph{soft-argmax}, a probability-weighted average that is only meaningful in a globally linear space. However, $(\theta,\rho)$ and $(\theta+\pi,-\rho)$ describe the same undirected line, so $H$ double-covers the space of undirected lines $H/\mathbb{Z}_2$: a Möbius strip, obtained by identifying each pair under $\mathbb{Z}_2$ action. Soft-argmax operates on the cover $H$, but since $H/\mathbb{Z}_2$ admits no linear structure, it tears geometrically adjacent lines apart. Thus we need a $\mathbb{Z}_2$-invariant embedding of lines into a linear space, on which soft-argmax is well-defined. We achieve this by parametrising lines via unit-norm homogeneous vectors $\ell=(1+\rho^2)^{-1/2}(\cos\theta,\sin\theta,-\rho)^{\top}\in\mathbb{R}^3$ and applying the Veronese map $v_2(\ell)=\ell\ell^{\top}$ that satisfies $v_2(\ell)=v_2(-\ell)$. This descends continuously to an embedding of the quotient $H/\mathbb{Z}_2$ into the linear space $\mathrm{Sym}^2(\mathbb{R}^3)$, where the antipodal ambiguity vanishes. Line extraction becomes a barycentre in $\mathrm{Sym}^2(\mathbb{R}^3)$, projected back via its leading eigenvector. We validate our \emph{Veronese soft-argmax} in a Hough transform-based network across all resolvable lines, confirming uniform and seam-free recovery. We further derive that the $L_2$-loss on isometrically weighted Veronese embeddings equals the squared chordal distance between lines in projective space, enabling a geometrically precise training objective.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.00521 — 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 2026-10-17T06:41:55.896Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).