Skip to content
@RePAIRProject

RePAIR Project

Reconstructing the Past: Artificial Intelligence and Robotics Meet Cultural Heritage

cover image for RePAIR project

‘RePAIR’ project is an acronym for Reconstructing the Past: Artificial Intelligence and Robotics meet Cultural Heritage. The project has received funding from the Horizon 2020 research and innovation program of the European Union, under Grant Agreement no. 964854. The main goal of RePAIR project is to develop a ground-breaking technology to virtually eliminate one of the most labour intensive and frustrating steps in archaeological research, namely the physical reconstruction of shattered artworks. Indeed, countless vases, amphoras, frescos and other ancient artefacts, all over the world, have not survived intact and were dug out from excavation sites as large collections of fragments, many of which are damaged, worn out or missing altogether. Reconstruction of small artefacts is typically done by experienced operators, possibly with the assistance of dedicated software, but when the number of fragments is large (say, of the order of thousands) manual or computer-assisted restoration is simply hopeless. This prevents a large fraction of the world’s cultural heritage from being openly accessible to scholars as well as the general public. By developing and integrating novel technologies in the fields of robotics, computer vision and artificial intelligence, we envisage a future where archaeology can deal effectively with reconstruction problems at an unprecedented scale and be able to bring back to life ancient artworks and masterpieces which would otherwise remain broken into pieces forever. Specifically, we aim to develop an intelligent robotic system which will autonomously process, match and physically assemble large fractured artefacts at a fraction of the time it takes humans to do. The level of ambition of our proposal poses several challenges that cannot be satisfactorily addressed with off-the-shelf technologies, and hence we shall develop brand-new solutions that will push the boundaries of research in the fields of robotics and computer vision. Our system will be tested over iconic case studies from the UNESCO World Heritage site of Pompeii, and one tangible outcome of the project will be to restore two world-renowned frescos which are now shattered into thousands of fragments and forgotten in storerooms.

Pinned Loading

  1. repair_ros_robot repair_ros_robot Public

    ROS package to control the simulated and real robot

    Python 3

  2. RL_puzzle_solver RL_puzzle_solver Public

    Solving Jigsaw Puzzles using Relaxation Labeling. Code relative to the paper: Nash Meets Wertheimer: Using Good Continuation in Jigsaw Puzzles (ACCV 2024)

    Python 1

  3. AAFR AAFR Public

    Reassembling Broken Objects using Breaking Curves (ICPR 2024)

    Python 8 3

  4. fragment-restoration fragment-restoration Public

    Semantic Motif Segmentation of Archaeological Fresco Fragments (ICCV Workshop on E-Heritage, 2023)

    JavaScript 3

  5. repair_ground_truth repair_ground_truth Public

    Guide for creating the ground truth for the RePAIR Project

    Python

  6. 2DPuzzleSolving-tool 2DPuzzleSolving-tool Public

    Forked from xmlyqing00/PuzzleSolving-tool

    A fork of the original tool (https://xmlyqing00.github.io/PuzzleSolving-tool/) for 2d puzzle solving focusing on extending command line generation

    JavaScript 2 2

Repositories

Showing 10 of 18 repositories
  • RL_puzzle_solver Public

    Solving Jigsaw Puzzles using Relaxation Labeling. Code relative to the paper: Nash Meets Wertheimer: Using Good Continuation in Jigsaw Puzzles (ACCV 2024)

    RePAIRProject/RL_puzzle_solver’s past year of commit activity
    Python 1 CC0-1.0 0 0 0 Updated Dec 17, 2024
  • 3D-baselines Public
    RePAIRProject/3D-baselines’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Dec 12, 2024
  • fragment_digitization Public

    Pipeline and scripts for digitizing the scanned frescoes.

    RePAIRProject/fragment_digitization’s past year of commit activity
    Python 0 0 0 0 Updated Dec 12, 2024
  • 2D-baselines Public
    RePAIRProject/2D-baselines’s past year of commit activity
    Python 0 0 0 0 Updated Dec 12, 2024
  • AAFR Public

    Reassembling Broken Objects using Breaking Curves (ICPR 2024)

    RePAIRProject/AAFR’s past year of commit activity
    Python 8 CC0-1.0 3 2 0 Updated Dec 3, 2024
  • repair_motion_controller Public

    A ROS pkg for planning and executing goal trajectory utilizing klampt and xbot2.

    RePAIRProject/repair_motion_controller’s past year of commit activity
    Python 0 0 0 0 Updated Nov 19, 2024
  • RePAIR_dataset Public

    The webpage for the RePAIR dataset

    RePAIRProject/RePAIR_dataset’s past year of commit activity
    JavaScript 0 CC-BY-SA-4.0 0 0 0 Updated Nov 18, 2024
  • repair_ros_robot Public

    ROS package to control the simulated and real robot

    RePAIRProject/repair_ros_robot’s past year of commit activity
    Python 3 0 0 0 Updated Nov 8, 2024
  • pcd2images Public

    Rendering 2D images of the top surface from the 3D mesh

    RePAIRProject/pcd2images’s past year of commit activity
    Python 0 0 0 0 Updated Nov 7, 2024
  • repair_ground_truth Public

    Guide for creating the ground truth for the RePAIR Project

    RePAIRProject/repair_ground_truth’s past year of commit activity
    Python 0 0 0 0 Updated Nov 6, 2024

Top languages

Loading…

Most used topics

Loading…