Robots Vision and Perception Group

mad-icp

Minimal, robust, accurate and real-time LiDAR odometry

mdslam

MD-SLAM: Multi-cue Direct SLAM. Implements the first photometric LiDAR SLAM pipeline, that works withouth any explicit geometrical assumption. Universal approach, working independently for RGB-D and LiDAR.

srrg2_solver

ILS-based SLAM-focused solver

ba-mdslam

Photometric SLAM and Bundle Adjustment for RGB-D and LiDAR in CUDA.

srrg2_slam_interfaces

Plug-and-Play SLAM core repository. Atomic and compound SLAM modules

ca2lib

LiDAR-Camera calibration toolbox

vbr-devkit

Vision Benchmark in Rome Development Kit

learning-where-to-look

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information

srrg2-hipe

Hierarchical Initialization for Pose Graphs

srrg2_proslam

SRRG 3D RGB-D/Stereo SLAM suite. Specialization of srrg2_slam_interfaces

srrg2_laser_slam_2d

SRRG 2D laser SLAM suite. Specialization of srrg2_slam_interfaces

srrg2_apriltag_calibration

Offline extrinsic calibration between dense 3D-LiDAR and monocular, based on the AprilTag3 library

srrg2_core

Core data structures, geometry related stuff, point clouds and utilities

srrg2_config_visualizer

SRRG GUI for configuration files editing.

pyprojections

Multiple pythonic image projections for robotics and computer vision applications

srrg2_executor

SRRG console to run SLAM systems

srrg2_qgl_viewport

Basic OpenGL viewport in the SRRG2 multiverse - based on QGLViewer Library

vbr-view

Dataset pointclouds visualization using Potree

OneFormer

OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023

srrg2_cmake_modules

CMake Modules for external libraries

vbr-slam-benchmark