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

Tsesmelis, Theodore; Palmieri, Luca; Khoroshiltseva, Marina; Islam, Adeela; Elkin, Gur; Itzhak Shahar, Ofir; Scarpellini, Gianluca; Fiorini, Stefano; Ohayon, Yaniv; Alali, Nadav; Aslan, Sinem; Morerio, Pietro; Vascon, Sebastiano; gravina, Elena; Cristina Napolitano, Maria; Scarpati, Giuseppe; zuchtriegel, Gabriel; Spühler, Alexandra; Fuchs, Michel E.; James, Stuart; Ben-Shahar, Ohad; Pelillo, Marcello; Del Bue, Alessio

Abstract

This paper proposes the RePAIR dataset that represents a challenging benchmark to test modern computational and data driven methods for puzzle-solving and reassembly tasks. Our dataset has unique properties that are uncommon to current benchmarks for 2D and 3D puzzle solving. The fragments and fractures are realistic, caused by a collapse of a fresco during a World War II bombing at the Pompeii archaeological park. The fragments are also eroded and have missing pieces with irregular shapes and different dimensions, challenging further the reassembly algorithms. The dataset is multi-modal providing hi-res images with characteristic pictorial elements, detailed 3D scans of the fragments and meta-data annotated by the archaeologists. Ground truth has been generated through several years of unceasing fieldwork, including the excavation and cleaning of each fragment, followed by manual puzzle solving by archaeologists of a subset of 1,000 pieces among the 16,000 available. After digitizing all the fragments in 3D, a benchmark was prepared to challenge current reassembly and puzzle-solving methods that often solve more simplistic synthetic scenarios. The tested baselines show that there clearly exists a gap to fill in solving this computationally complex problem.

Citation

Tsesmelis, T., Palmieri, L., Khoroshiltseva, M., Islam, A., Elkin, G., Itzhak Shahar, O., Scarpellini, G., Fiorini, S., Ohayon, Y., Alali, N., Aslan, S., Morerio, P., Vascon, S., gravina, E., Cristina Napolitano, M., Scarpati, G., zuchtriegel, G., Spühler, A., Fuchs, M. E., James, S., …Del Bue, A. (2024, December). Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving. Presented at Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track, Vancouver, Canada

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Conference on Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track
• Start Date: Dec 10, 2024
• End Date: Dec 15, 2024
• Acceptance Date: Sep 26, 2024
• Deposit Date: Oct 23, 2024
• Peer Reviewed: Peer Reviewed
• Public URL: https://durham-repository.worktribe.com/output/2981636
• Publisher URL: https://www.proceedings.com/