lucasb-eyer/pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.
This tool helps improve the accuracy of image segmentation and labeling. You provide an image along with an initial, possibly rough, pixel-level classification (e.g., from a deep learning model or a simple algorithm). The tool then refines these classifications, producing a more precise and coherent segmentation where neighboring pixels with similar properties are more likely to belong to the same category. This is useful for researchers and practitioners working with image analysis and computer vision tasks.
2,013 stars. No commits in the last 6 months.
Use this if you need to refine initial pixel classifications in images to achieve smoother, more accurate segmentation results.
Not ideal if your primary goal is real-time processing or if you are looking for a standalone segmentation algorithm rather than a refinement tool.
Stars
2,013
Forks
425
Language
C++
License
MIT
Category
Last pushed
Mar 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lucasb-eyer/pydensecrf"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
patrick-llgc/Learning-Deep-Learning
Paper reading notes on Deep Learning and Machine Learning
eric-yyjau/pytorch-superpoint
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
magicleap/SuperGluePretrainedNetwork
SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)
changhao-chen/deep-learning-localization-mapping
A collection of deep learning based localization models
zhou13/lcnn
LCNN: End-to-End Wireframe Parsing