AI Chat AI Image Generator AI Video Text to Speech

3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversary Network

11/17/2017

∙

by Renato Hermoza, et al.

∙

∙

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.

Renato Hermoza
4 publications
Ivan Sipiran
6 publications

page 1

page 5

page 6

research

∙ 11/17/2017

Shape Inpainting using 3D Generative Adversarial Network and Recurrent Convolutional Networks

Recent advances in convolutional neural networks have shown promising re...

0 Weiyue Wang, et al. ∙

research

∙ 07/29/2017

Improved Adversarial Systems for 3D Object Generation and Reconstruction

This paper describes a new approach for training generative adversarial ...

0 Edward Smith, et al. ∙

research

∙ 12/03/2019

It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality

In this paper, we propose in our novel generative framework the use of G...

0 Charan D. Prakash, et al. ∙

research

∙ 01/15/2023

Inpainting borehole images using Generative Adversarial Networks

In this paper, we propose a GAN-based approach for gap filling in boreho...

0 Rachid Belmeskine, et al. ∙

research

∙ 04/07/2022

MDA GAN: Adversarial-Learning-based 3-D Seismic Data Interpolation and Reconstruction for Complex Missing

The interpolation and reconstruction of missing traces is a crucial step...

0 YiMin Dou, et al. ∙

research

∙ 02/01/2018

3D Object Dense Reconstruction from a Single Depth View

In this paper, we propose a novel approach, 3D-RecGAN++, which reconstru...

0 Bo Yang, et al. ∙

research

∙ 02/01/2017

Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit

Observations of astrophysical objects such as galaxies are limited by va...

0 Kevin Schawinski, et al. ∙