DaniilSinitsyn/colmap_cameras_pytorch
Colmap camera models implemented in PyTorch
This project offers PyTorch implementations of various camera models, like those used in COLMAP, to help reconstruct 3D scenes or perform 3D measurements from images. You can input camera parameters and 3D points or 2D pixels, and it will output either pixel coordinates or 3D rays. It's designed for researchers and engineers working on computer vision tasks such as photogrammetry, visual effects, or robotics.
Use this if you need to accurately model real-world camera optics and optimize their parameters within a deep learning framework for tasks like 3D reconstruction, augmented reality, or pose estimation.
Not ideal if you are looking for a standalone application for end-users to process images without programming, or if your primary focus is on standard image processing without geometric camera modeling.
Stars
16
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DaniilSinitsyn/colmap_cameras_pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
alicevision/AliceVision
3D Computer Vision Framework
colmap/colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
ANTsX/ANTs
Advanced Normalization Tools (ANTs)
alicevision/Meshroom
Node-based Visual Programming Toolbox
MOLAorg/mola
A Modular Optimization framework for Localization and mApping (MOLA)