← Search

Tapas Kumar Dutta

1 accepted papers

2025

SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models

CVPR 2025poster

While foundation models have revolutionised computer vision, their effectiveness for sketch understanding remains limited by the unique challenges of abstract, sparse visual inputs. Through systematic analysis, we uncover two fundamental limitations: Stable Diffusion (SD) struggles to extract meanin…

Cited by 0SourcePDFScholar