Newest papers

Open-Form Geometric Style Transfer

A. Elad, Gal Metzer, Omer Dahari, Min Lu, Daniel Cohen‐Or · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26820 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Un estilo geométrico aprendido de una familia de formas se aplica típicamente a nuevas formas de la misma familia. Consideramos un entorno más desafiante: aprender el lenguaje de diseño geométrico de un alfabeto latino estilizado y aplicarlo a nuevas formas, desde glifos griegos a estructuras completamente diferentes como las posturas humanas. Introducimos Open-Form Geometric Style Transfer, donde las formas a las que se puede aplicar un estilo geométrico aprendido no se limitan a la familia de formas en la que se observó ese estilo. Este entorno es desafiante: la dificultad no es simplemente aprender un estilo, sino aprender el estilo sin aprender la familia de formas en la que se observó. Representamos las formas por esquemas estructurales y desencadenamos la adherencia estructural de la realización del estilo usando una familia de Geometría LoRA y una

Machine translation (Meta M2M100); the English original follows.

Abstract

A geometric style learned from one family of shapes is typically applied to new shapes from the same family. We consider a more challenging setting: learning the geometric design language of a stylized Latin alphabet and applying it to new forms, from Greek glyphs to entirely different structures such as human poses. We introduce Open-Form Geometric Style Transfer, where the forms to which a learned geometric style can be applied are not restricted to the shape family in which that style was observed. This setting is deceptively challenging: the difficulty is not merely learning a style, but learning the style without learning the shape family in which it was observed. We represent target forms by structural sketches and disentangle structural adherence from style realization using a Geometry LoRA and a style-specific LoRA. Critically, open-form transfer requires the Geometry LoRA to be universal. To achieve this, we devise a geometry-enrichment strategy that constructs a large and purposefully diverse collection of synthetic structural sketches spanning a broad range of unfamiliar geometries. Our experiments and ablations demonstrate the importance of both disentanglement and this universal geometry prior, enabling geometric styles learned from glyphs, pictograms, and other shape families to be transferred to substantially different, unseen forms.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Style (visual arts), Stylized fact, Artificial intelligence, Computer science, Geometric shape, Alphabet

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange