Object-Level Access to SVG Scenes: A Benchmark and Raster-Grounded Method for Text-Guided Vector Object Extraction
This work introduces text-guided vector object extraction, where the goal is to recover an editable sub-SVG corresponding to a natural-language query, and proposes a raster-grounded extraction method that localizes the queried object in the rendered image and maps the resulting region back to SVG primitives through ove...