# 3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversarial Network

arXiv: https://arxiv.org/abs/1711.06363 · HTML: https://mlsanity.com/paper/1711.06363/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2017.

## Built on by (most cited first, 12 of 12)

- [Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving](https://mlsanity.com/paper/2410.24010/) (2024)
- [Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts](https://mlsanity.com/paper/2303.14152/) (2023)
- [Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation](https://mlsanity.com/paper/2107.06941/) (2021)
- [3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers](https://mlsanity.com/paper/2110.08861/) (2021)
- [DeepMend: Learning Occupancy Functions to Represent Shape for Repair](https://mlsanity.com/paper/2210.05728/) (2022)
- [DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repair](https://mlsanity.com/paper/2211.12400/) (2022)
- [Cultural Heritage 3D Reconstruction with Diffusion Networks](https://mlsanity.com/paper/2410.10927/) (2024)
- [Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks](https://mlsanity.com/paper/2107.02909/) (2021)
- [SR-CurvANN: Advancing 3D Surface Reconstruction through Curvature-Aware Neural Networks](https://mlsanity.com/paper/2407.17896/) (2024)
- [Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration](https://mlsanity.com/paper/2503.04030/) (2025)
- [Pix2Repair: Implicit Shape Restoration from Images](https://mlsanity.com/paper/2305.18273/) (2023)
- [3D Shape Generation: A Survey](https://mlsanity.com/paper/2506.22678/) (2025)

## Abstract (arXiv)

We introduce a data-driven approach to aid the repairing and conservation of archaeological objects: ORGAN, an object reconstruction generative adversarial network (GAN). By using an encoder-decoder 3D deep neural network on a GAN architecture, and combining two loss objectives: a completion loss and an Improved Wasserstein GAN loss, we can train a network to effectively predict the missing geometry of damaged objects. As archaeological objects can greatly differ between them, the network is conditioned on a variable, which can be a culture, a region or any metadata of the object. In our results, we show that our method can recover most of the information from damaged objects, even in cases where more than half of the voxels are missing, without producing many errors.