Arnaud Gueze

Deformable Polygonal Flow Matching with Informed Priors and Hierarchical Graph Constraints

This paper presents a novel method, called Deformable Polygonal Flow Matching (DPFM), for the generation of polygonal arrangements such as jigsaw puzzles and floor plans. DPFM is a Flow Matching framework that enables the generation process to deform, rotate, and translate polygons while decoupling