Caffe: a fast open framework for deep learning.

Real-Time 3D Semantic Reconstruction from 2D data

Real time semantic slam in ROS with a hand held RGB-D camera

An open source advanced driver assistance system (ADAS) that uses Jetson Nano as the hardware. Features: Traffic sign detection, Forward collision warning, Lane departure warning.

A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.

Be Driven 🚘

Deep Learning sample programs using PyTorch in C++

[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

Direct Graphical Models (DGM) C++ library, a cross-platform Conditional Random Fields library, which is optimized for parallel computing and includes modules for feature extraction, classification and visualization.

Free and open source semantic segmentation of 3D point clouds, fast and memory efficient.

A label tool aim to reduce semantic segmentation label time, rectangle and polygon annotation is supported

Code for ECCV 2020 paper (oral): Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

🍀 Pytorch Implementation of RandLA-Net (https://arxiv.org/abs/1911.11236)

TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes

[CVPR2021] SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation

Lane detection model for mobile device via MNN project

Rangenet++ with high-version TensorRT (e.g.8~10), libtorch, CUDA programming.

一个简单的TensorRT实现语义分割的C++程序

Real-time CPU person segmentation for privacy in video calls