# Artificial Intelligence Generated Coins for Size Comparison

arXiv: https://arxiv.org/abs/2301.04751 · HTML: https://mlsanity.com/paper/2301.04751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 11 Jan 2023.

## Builds on (most cited first, 7 of 7)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Adversarial Text-to-Image Synthesis: A Review](https://mlsanity.com/paper/2101.09983/) (2021)
- [Unsupervised Statistical Learning for Die Analysis in Ancient Numismatics](https://mlsanity.com/paper/2112.00290/) (2021)

## Abstract (arXiv)

Authors of scientific articles use coins in photographs as a size reference for objects. For this purpose, coins are placed next to objects when taking the photo. In this letter we propose a novel method that uses artificial intelligence (AI) generated images of coins to provide a size reference in photos. The newest generation is able to quickly generate realistic high-quality images from textual descriptions. With the proposed method no physical coin is required while taking photos. Coins can be added to photos that contain none. Furthermore, we show how the coin motif can be matched to the object.