Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving

<p><em>Accepted by NeurIPS 2024 Datasets and Benchmarks Track</em></p> <p>We introduce the RePair puzzle-solving dataset, a large-scale real world dataset of fractured frescoes from the archaelogical campus of Pompeii. Our dataset consists of over 1000 fractured frescoes. The RePAIR stands as a realistic computational challenge for methods for 2D and 3D puzzle solving, and serves as a benchmark that enables the study of fractured object reassembly and presents new challenges for geometric shape understanding. Please visit <a href="https://repairproject.github.io/RePAIR_dataset/">our website</a> for more dataset information, access to source code scripts and for an interactive gallery viewing of the dataset samples.</p> <div> <h3>Access the entire dataset</h3> <p>We provide a compressed version of our dataset in two seperate files. One for the 2D version and one for the 3D version.</p> <p>Our full dataset contains over one thousand individual fractured fragments divided into groups with its corresponding folder and all compressed into their individual sub-set format regarding whether they are 2D or 3D. Regarding the 2D dataset, each fragment is saved as a .PNG image and each group has the corresponding ground truth transformation to solve the puzzle as a <strong><em>.TXT</em></strong> file. Considering the 3D dataset, each fragment is saved as a mesh using the widely <strong><em>.OBJ</em></strong> format with the corresponding material (<strong><em>.MTL</em></strong>) and texture (<strong><em>.PNG</em></strong>) file. The meshes are already in the assembled position and orientation, so that no additional information is needed.&nbsp; All additional metadata information are given as <strong><em>.JSON</em></strong> files.</p> <p>&nbsp;</p> <h1>Important Note</h1> <p><strong>Please be advised that downloading and reusing this dataset is permitted only upon acceptance of the following license terms.</strong></p> <p><em><strong>The Istituto Italiano di Tecnologia (IIT) declares, and the user (&ldquo;User&rdquo;) acknowledges, that the "RePAIR puzzle-solving dataset" contains 3D scans, texture maps, rendered images and meta-data of fresco fragments acquired at the Archaeological Site of Pompeii. IIT is authorised to publish the RePAIR puzzle-solving dataset herein only for scientific and cultural purposes and in connection with an academic publication referenced as Tsemelis et al., "Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving", NeurIPS 2024. Use of the &nbsp;RePAIR puzzle-solving dataset by User is limited to downloading, viewing such images; comparing these with data or content in other datasets. User is not authorised to use, in particular explicitly excluding any commercial use nor in conjunction with the promotion of a commercial enterprise and/or its product(s) or service(s), reproduce, copy, distribute the &nbsp;RePAIR puzzle-solving dataset. User will not use the &nbsp;RePAIR puzzle-solving dataset in any way prohibited by applicable laws. &nbsp;RePAIR puzzle-solving dataset therein is being provided to User without warranty of any kind, either expressed or implied. User will be solely responsible for their use of such &nbsp;RePAIR puzzle-solving dataset. In no event shall IIT be liable for any damages arising from such use.</strong></em></p> </div>