PortraitNet
Portrait seg model
A real-time portrait segmentation model developed for efficient deployment on mobile devices
Code for the paper "PortraitNet: Real-time portrait segmentation network for mobile device" @ CAD&Graphics2019
288 stars
7 watching
61 forks
Language: Jupyter Notebook
last commit: over 5 years ago
Linked from 1 awesome list
mobileportraitsegmentation
Related projects:
Repository | Description | Stars |
---|---|---|
| This project presents two lightweight deep learning models for portrait segmentation, along with their implementation and training procedures. | 62 |
| An open-source implementation of an image segmentation model that combines background removal and object detection capabilities. | 1,484 |
| This project provides code and pre-trained models for object segmentation in videos using a spatial propagation network. | 144 |
| An implementation of real-time semantic segmentation using a deep neural network architecture, | 406 |
| A deep learning implementation of a multi-path network architecture for medical image segmentation | 140 |
| A PyTorch implementation of a deep learning model for semantic image segmentation | 1,598 |
| An implementation of the SegNet-Basic deep learning model for image segmentation using Keras and convolutional neural networks. | 83 |
| An implementation of a deep learning model for instance segmentation and monocular depth estimation. | 79 |
| A tool for cell instance aware segmentation in densely packed 3D volumetric images | 101 |
| A TensorFlow-based implementation of a semantic segmentation network for image classification tasks | 326 |
| A Python implementation of a Generative Adversarial Network (GAN) model used to generate portraits from latent codes. | 40 |
| A deep neural network architecture for segmenting images into distinct regions of interest | 205 |
| An implementation of human instance segmentation based on pose estimation | 529 |
| Develops an instance segmentation and panoptic segmentation model for computer vision tasks. | 648 |
| This project provides code for training image question answering models using stacked attention networks and convolutional neural networks. | 108 |