RohanG9929/LoFTR-in-Tensorflow
Code for our re-implementation of "LoFTR: Detector-Free Local Feature Matching with Transformers"
This project helps computer vision practitioners find matching points between two images without needing a separate feature detection step. You input a pair of images, and it outputs a set of corresponding points, useful for tasks like 3D reconstruction or panorama stitching. Computer vision researchers or engineers working with image alignment would use this.
No commits in the last 6 months.
Use this if you need to identify precise correspondences between visual features in different images for tasks like image stitching or object recognition.
Not ideal if you require the absolute highest accuracy for feature matching, as this re-implementation needs further training to reach the performance of the original algorithm.
Stars
8
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RohanG9929/LoFTR-in-Tensorflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...