TapasKumarDutta1/SketchFusion

[CVPR 2025] Official Implementation of paper 'SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models'

36
/ 100
Emerging

This helps computer vision researchers and AI practitioners better understand and process hand-drawn sketches. It takes a sketch as input and can perform tasks like recognizing what the sketch depicts, finding similar sketches or photos, identifying specific parts within a sketch for segmentation, or establishing correspondences between a sketch and a photo. It's designed for those working with visual recognition systems that need to interpret abstract, sparse sketch inputs.

No commits in the last 6 months.

Use this if you are developing AI applications that need to accurately interpret and utilize hand-drawn sketches for tasks like image search, object recognition, or detailed image analysis.

Not ideal if your primary focus is on processing high-detail photographic images without any sketch-based interaction.

sketch-recognition image-retrieval image-segmentation computer-vision AI-model-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

15

Forks

3

Language

Python

License

MIT

Last pushed

Mar 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TapasKumarDutta1/SketchFusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.