closed-form-matting
Image segmentation software
Provides an implementation of image matting and background/foreground reconstruction from images with scribbles or trimaps.
Python implementation of A. Levin D. Lischinski and Y. Weiss. A Closed Form Solution to Natural Image Matting. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2006, New York
438 stars
14 watching
107 forks
Language: Python
last commit: almost 2 years ago image-mattingimage-processinglaplacianmattingpython
Related projects:
Repository | Description | Stars |
---|---|---|
| A deep learning model for image matting that provides foreground, background, and alpha predictions | 469 |
| Python implementation of an image matting method using Poisson equations | 49 |
| An implementation of a deep learning model for separating foreground and background in images | 626 |
| Deep learning implementation of image matting, aiming to separate foreground and background from input images. | 293 |
| An implementation of deep image matting in PyTorch using a neural network architecture. | 821 |
| An implementation of KNN Matting, a technique for segmenting foreground from background in images. | 150 |
| A transformer-based image matting model using prior-tokens and self-attention mechanisms to remove background from images. | 223 |
| A software framework for training and evaluating full-resolution residual networks for semantic image segmentation tasks | 280 |
| A large dataset of human matting images and corresponding results for training person segmentation models. | 615 |
| A library of fast computer vision algorithms implemented in C++ for speed, operating over numpy arrays. | 855 |
| An implementation of a deep learning system for semantic image segmentation using a combination of convolutional neural networks and conditional random fields. | 239 |
| A Python library for alpha matting algorithms and foreground estimation methods. | 1,791 |
| A toolbox for unsupervised multilabel image segmentation using the Potts model. | 110 |
| An adversarial framework for generating stylized images through an iterative process of optimizing and refining the output based on comparison to both content and texture images. | 128 |
| Develops an object segmentation algorithm to detect camouflaged objects in images with varying backgrounds and contexts. | 20 |