tgxs002/wikiscenes

Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision. ICCV 2021.

34
/ 100
Emerging

This project offers a comprehensive dataset of religious landmarks, primarily cathedrals, with associated images, textual descriptions, and detailed 3D geometric information. It takes in vast amounts of raw image data and text, alongside 3D models and keypoint correspondences, to produce a structured collection for advanced computer vision research. This is ideal for researchers in computer vision, photogrammetry, and 3D reconstruction who need rich, multi-modal data for training and evaluating models.

No commits in the last 6 months.

Use this if you are developing or evaluating computer vision models that need to understand scenes by combining visual information with language and 3D structure, especially for large architectural landmarks.

Not ideal if you are looking for a simple tool to process individual images or texts, or if your domain is outside of complex architectural scene understanding.

3D Reconstruction Computer Vision Research Architectural Scene Understanding Multimodal Data Analysis Cultural Heritage Digitization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

43

Forks

4

Language

Python

License

Last pushed

Apr 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tgxs002/wikiscenes"

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