SLAM is mainly divided into two parts: the front end and the back end. The front end is the visual odometer (VO), which roughly estimates the motion of the camera based on the information of adjace…

This is the project page of the paper "Flow-Motion and Depth Network for Monocular Stereo and Beyond''

A robust LiDAR Odometry and Mapping (LOAM) package for Livox-LiDAR

Additional Code for the GN-Net benchmark. The data is available at http://vision.in.tum.de/gn-net

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

lane segmentation pytorch

Code for "Self-Supervised 3D Keypoint Learning for Ego-motion Estimation"

Lane detection model for mobile device via MNN project

A General Simultaneous Localization and Mapping Framework which supports feature based or direct method and different sensors including monocular camera, RGB-D sensors or any other input types can …

The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

hair segmentation in mobile device

Soft for Dobot Magician for stand-alone sorting objects using TensorFlow API, OpenCV, pydobot.

Android video semantic segmentation using DeeplabV3+ lite

Documentations for PaddlePaddle

Official implementation of "PifPaf: Composite Fields for Human Pose Estimation" in PyTorch.

MNN is a lightweight deep neural network inference engine.

Lane segmentation model trained with tensorflow implementation of Fast-SCNN

A high performance semantic segmentation toolkit based on PaddlePaddle. (『飞桨』图像分割库）

Learning Matchable Image Transformations

Awesome Knowledge Distillation

DeepLabV3+ implemented in TensorFlow2.0

🤘 awesome-semantic-segmentation

Portrait segmentation with mobile-unet using keras

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

Amazing Semantic Segmentation on Tensorflow && Keras (include FCN, UNet, SegNet, PSPNet, PAN, RefineNet, DeepLabV3, DeepLabV3+, DenseASPP, BiSegNet)

Kaggle competition solutions