u2net

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

✂️ Automated high-quality background removal framework for an image using neural networks. ✂️

The Tensorflow, Keras implementation of U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET with optional ImageNet-trained backbones.

This repo contains code and a pre-trained model for clothes segmentation.

Huggingface cloth segmentation using U2NET

Python GUI for Interactive Image Background Removal using locally running AI point and click models such as Segment Anything and automatic whole-image models such as BiRefNet and Rembg

U-2-Net: U Square Net - Modified for paired image training of style transfer

Nested U-Net with two-level skip connections for speech enhancement

胃癌恶性病变组织检测

基于显著性目标检测的非特定类别图像分割-中国大学生服务外包创新创业大赛

Copy objects from real life and directly paste them on a background image using only your phone's camera

Implementation of the paper "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection" in TensorFlow.

U2Net + ISNet GT encoder, training base on ssim loss, iou loss and bce loss，experimented on tooth segmentation on panoramic X-ray images.

Preview clothing with live camera overlays or generate a photo try-on from person and garment images. The application combines a Next.js interface, a FastAPI garment-processing API, and CatVTON inference through a hosted Gradio service.

Privacy-first offline AI background remover and batch image resizer for Windows.

Minimal scripts for testing U-2-Net models in Keras

Light, cleaned version of U2NET model

It should take a photo containing clothing as input, and then output the masked and cropped photo

Open-source background removal research workbench with Rust algorithms, Python/OpenCV classical methods, ONNX ML adapters, benchmarks, docs, and equation visualizations.

The project involves training a U2-Net Lite model for human segmentation using the P3M-10k dataset. Human segmentation refers to the process of accurately separating the human body from the background in an image or video.