Stars
This package provides localization in a pre-built map using ICP and odometry (or the IMU measurements).
Unsupervised Scale-consistent Depth Learning from Video (IJCV2021 & NeurIPS 2019)
Official implementation of the paper "Self-supervised Depth and Ego-motion Estimation for Monocular Thermal Video using Multi-spectral Consistency Loss"
Repository of 3D Object Detection with Pointformer (CVPR2021)
[3DV 2021] DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
[CVPR 2022] Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding
Robust Equivariant Imaging (REI), CVPR'2022 Oral
[CVPR Oral 2022] PyTorch Implementation for "Learning to Deblur using Light Field Generated and Real Defocused Images"
Code release for "BoxeR: Box-Attention for 2D and 3D Transformers"
Unofficial implementation of "Deepvo: Towards end-to-end visual odometry with deep recurrent convolutional neural networks"
LIBSVM -- A Library for Support Vector Machines
SVM & PCA Based RPE BreakPoint Detaction
This is an implementation of CVPR 2019 accepted paper "SOSNet: Second Order Similarity Regularization for Local Descriptor Learning" , and because of the training process was not public, I will try…
Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]
VIO_Learning. A simple implement of mono msckf in https://github.com/TurtleZhong/msckf_mono/tree/master/src/msckf_mine_1.0
LVI-SAM: Tightly-coupled Lidar-Visual-Inertial Odometry via Smoothing and Mapping
Light-weight camera LiDAR calibration package for ROS using OpenCV and PCL (PnP + LM optimization)
A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points…
Pretrained pytorch model for the SOSNet descriptor [CVPR 2019]
针对带有RGBD相机的服务机器人，物流机器人等。具有：语义地图构建、定位导航、三维重构、重定位、动态物体识别、移动避障、手势识别、人脸识别、语音合成与识别等功能
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 …
Deploy your model with TensorRT quickly.
📚 The list of vision-based SLAM / Visual Odometry open source, blogs, and papers