The semantic parsing of building facade images is a fundamental yet challenging task in urban scene understanding. Existing works sought to tackle this task by using facade grammars or convolutional ...

We propose a sequential optimization technique for segmenting a rectified image of a facade into semantic categories. Our method retrieves a parsing which respects common architectural constraints and ...

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting Dolphin (Do cument Image P arsing via H eterogeneous Anchor Prompt in g) is a novel multimodal document image parsing model following ...

Document image parsing is challenging due to its complexly intertwined elements such as text paragraphs, figures, formulas, and tables. Dolphin addresses these challenges through a two-stage approach: ...