tgxs002/wikiscenes
Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision. ICCV 2021.
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.
Stars
43
Forks
4
Language
Python
License
—
Category
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.
Higher-rated alternatives
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)