snooble

openvslam

OpenVSLAM: A Versatile Visual SLAM Framework

solve_keyframe_pose_graph

A kidnap-aware multi-threaded node to solve 6DOF posegraph slam. Needs poses at each node (subscribes to) and relative positions at edges. Maintains an optimized pose graph. Has support for recovery from kidnap

CenterNet

Object detection, 3D detection, and pose estimation using center point detection:

CenterNet

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

VINS-Fusion

An optimization-based multi-sensor state estimator

VINS-Mono

A Robust and Versatile Monocular Visual-Inertial State Estimator

A-LOAM

Advanced implementation of LOAM

second.pytorch

PointPillars for KITTI object detection

MASC

SSD

High quality, fast, modular reference implementation of SSD in PyTorch

pytorch-faster-rcnn

pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

poselstm-pytorch

PyTorch implementation of PoseLSTM and PoseNet

pyslam

Non-linear least-squares SLAM in Python using scipy and numpy. Modelled after Google's Ceres solver.

liegroups

Python implementation of SO2, SE2, SO3, and SE3 matrix Lie groups using numpy or pytorch

PoseNet-Pytorch

Implementation of PoseNet using pytorch

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

pytorch-NetVlad

Pytorch implementation of NetVlad including training on Pittsburgh.

NetVLAD-pytorch

PyTorch implementation of NetVLAD & Online Hardest Triplet Loss.

PointSeg

bdd100k

This repo has been moved to https://github.com/bdd100k/bdd100k permanently.

simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper

GeoNet

Code for GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)

pytorch-mono-depth

Monocular depth prediction with PyTorch

LKVOLearner

Learning Depth from Monocular Videos using Direct Methods, CVPR 2018

easy-faster-rcnn.pytorch

An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.

PSMNet

Pyramid Stereo Matching Network (CVPR2018)

lvt

Lightweight Visual Tracking: A multipurpose visual odometry system.

deeplab-pytorch

PyTorch re-implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC datasets

semantic_slam

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

keras_frcnn

Keras Implementation of faster-rcnn