Research
📓 A curated list of deep learning image matting papers and codes
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
This is the repository to the paper "Flow based video matting" by Zijian Kuang and Xinran Tie. We proposed to use optical flow and UNet to generate a refined mask for video matting purpose.
A Trimap-Free Portrait Matting Solution in Real Time [AAAI 2022]
Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …
An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.
Github project for Attention-guided Temporal Coherent Video Object Matting.
MaskTrackRCNN for video instance segmentation based on mmdetection
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries.
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Official repository for Instance Human Matting via Mutual Guidance and Multi-Instance Refinement
Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
Real-time portrait segmentation for mobile devices
A collection of AWESOME things about image matting.
The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
This Repository is implementation of majority of Semantic Segmentation Loss Functions