adityamwagh/pose-estimation-loftr
Pose estimation pipeline for 3D Reconstruction using LoFTR (Local Feature Transformer) detector free feature matcher.
This project helps computer vision practitioners accurately determine the relative position and orientation of cameras that captured two different images of the same scene. It takes a pair of images (like photos of a building from different angles) and identifies corresponding points between them, even under challenging conditions. The output is a 'fundamental matrix' that describes how the cameras are positioned relative to each other, which is crucial for tasks like building 3D models or stitching panoramas.
No commits in the last 6 months.
Use this if you need to precisely match features between diverse images to understand camera positions for 3D reconstruction, simultaneous localization and mapping (SLAM), or panoramic stitching.
Not ideal if your primary goal is basic image comparison or object detection rather than detailed geometric understanding of camera pose.
Stars
23
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/adityamwagh/pose-estimation-loftr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvg/LightGlue
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
shariqfarooq123/AdaBins
Official implementation of Adabins: Depth Estimation using adaptive bins
amusi/CVPR2026-Papers-with-Code
CVPR 2026 论文和开源项目合集
isl-org/ZoeDepth
Metric depth estimation from a single image
daviddmc/NeSVoR
NeSVoR is a package for GPU-accelerated slice-to-volume reconstruction.