a lightweight image matting model
-
Updated
Feb 7, 2020 - Python
a lightweight image matting model
Simplified Deep Image Matting training code with keras on tensorflow
Predicting an alpha matte from an image and a trimap.
BackgroundRemover lets you Remove Background from images and video with a simple command line interface
Python implementation of a Bayesian approach to Natural Image Matting from Yung-Yu Chuang, Brian Curless, David H. Salesin, and Richard Szeliski. A Bayesian Approach to Digital Matting. In Proceedings of IEEE Computer Vision and Pattern Recognition (CVPR 2001), Vol. II, 264-271, December 2001
Background removal refers to the process of separating and eliminating the background of an image or video, leaving only the subject or foreground visible.
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
[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting
[IJCAI'21] Deep Automatic Natural Image Matting
[ACM MM 2021] Privacy-Preserving Portrait Matting
This project showcases an implementation of the U2-Net architecture for Image Matting in the TensorFlow.
A High-Efficient Research Development Toolkit for Image Segmentation Based on Pytorch.
Semantic matting project using image segmentation and image matting
[CVPR2021]Learning Affinity-Aware Upsampling for Deep Image Matting
Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution Salient Object Detection (ACCV 2022)
a simple online image matting web based on cv_unet_image-matting and cv_unet_universal-matting model
The official repo for [IJCV'23] "Rethinking Portrait Matting with Privacy Preserving"
[CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting
Add a description, image, and links to the image-matting topic page so that developers can more easily learn about it.
To associate your repository with the image-matting topic, visit your repo's landing page and select "manage topics."