Testing mediapipe capabilities to implement a background removal app

A Trimap-Free Solution for Portrait Matting in Real Time under Changing Scenes

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

Predicting an alpha matte from an image and a trimap.

php实现服务端自动抠图

This is tensorflow implementation for paper "Deep Image Matting"

RemoveBG PLUS: Extract Anything stands out as a user-centric AI vision model, the PLUS version of Remove BG, providing unparalleled flexibility and customization. It satisfies every content extraction need you may have from images and achieves significant advancements in functionality, performance, and efficiency.

Remove backgrounds by color selection

Python implementation of paper "A Bayesian approach to digital matting"

This script assumes you have REMBG installed and a decent file manager on Linux. (thunar, caja, nautilus, dolphin) ect... The script will allow you to run REMBG on a file from a right click "open with" setting on Linux.

ViTMatte is a state-of-the-art image matting model. It leverages plain Vision Transformers (ViTs) to accurately estimate the foreground object in images and videos. We see ViTMatte, its architecture, practical implementation steps, and its contributions to th

An python implementation of Triangulation Matting with a speed of about 1.3sec per image (480 x 320 x 3).

👹 mattematte: A C++ ToolKit for matting, segmentation, SR and colorization with MNN, ONNXRuntime and Vulkan.

This project implements the Bayesian Matting technique described in 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 [1]

AI Image Processing, including matting, background changing, beauty, manual smoother, manual remover and Style Transfer tool.

simple background changer on photo

This is a test ready version of foamliu/Deep-Image-Matting. This project added a new prediction function by using the original pre-trained model.

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