lqql2012

3DObjectTracking

Algorithms and Publications on 3D Object Tracking

camera_calibration

Accurate geometric camera calibration with generic camera models

CamVox

A low-cost SLAM system based on camera and Livox lidar.

clash-for-linux-backup

基于Clash Core 制作的Clash For Linux备份仓库 A Clash For Linux Backup Warehouse Based on Clash Core

DeepFaceLab

DeepFaceLab is the leading software for creating deepfakes.

depth_clustering

:taxi: Fast and robust clustering of point clouds generated with a Velodyne sensor.

DSP-SLAM

[3DV 2021] DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

FAST_LIO_LC

The tight integration of FAST-LIO with Radius-Search-based loop closure module.

gici-open

GNSS/INS/Camera Integrated Navigation Library

GVINS

Tightly coupled GNSS-Visual-Inertial system for locally smooth and globally consistent state estimation in complex environment.

hope

A ROS package for extracting horizontal planes given point cloud input

LIO-SAM-GPU-ScanToMapOpt

A CUDA reimplementation of the line/plane odometry of LIO-SAM. A point cloud hash map (inspired by iVox of Faster-LIO) on GPU is used to accelerate 5-neighbour KNN search.

lullaby

A collection of C++ libraries designed to help teams develop virtual and augmented reality experiences

mlcc

Fast and Accurate Extrinsic Calibration for Multiple LiDARs and Cameras

open_vins

An open source platform for visual-inertial navigation research.

papers

Some papers that have been of great help in my work, especially in the fields of ML and DL.

prenet

PTI

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" https://arxiv.org/abs/2106.05744

puma

Poisson Surface Reconstruction for LiDAR Odometry and Mapping

r3live

A Robust, Real-time, RGB-colored, LiDAR-Inertial-Visual tightly-coupled state Estimation and mapping package

RingNet

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

ritm_interactive_segmentation

Reviving Iterative Training with Mask Guidance for Interactive Segmentation

roop

one-click deepfake (face swap)

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

SensorsCalibration

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

stable-diffusion

A latent text-to-image diffusion model

street-gaussians-ns

Unofficial implementation of "Street Gaussians for Modeling Dynamic Urban Scenes"

tandem

[CoRL 21'] TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo

VINS-Fusion-GPU-BA

A CUDA reimplementation of Bundle Adjustment for VINS-Fusion

VINS-GPS-Wheel