Soft-Argmax for the Projective Plane via the Veronese Embedding
The Veronese soft-argmax is validated in a Hough transform-based network across all resolvable lines, confirming uniform and seam-free recovery and the squared chordal distance between lines in projective space is derived, enabling a geometrically precise training objective.
Benjamin El-Zein, Dominik Eckert, Paul Zech et al.
· 0 citations