# Historical Astronomical Diagrams Decomposition in Geometric Primitives

arXiv: https://arxiv.org/abs/2403.08721 · HTML: https://mlsanity.com/paper/2403.08721/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Computer-Aided Design as Language](https://mlsanity.com/paper/2105.02769/) (2021)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design](https://mlsanity.com/paper/2007.08506/) (2020)
- [SketchGen: Generating Constrained CAD Sketches](https://mlsanity.com/paper/2106.02711/) (2021)
- [Vitruvion: A Generative Model of Parametric CAD Sketches](https://mlsanity.com/paper/2109.14124/) (2021)
- [Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries](https://mlsanity.com/paper/2211.15658/) (2022)
- [Anchor DETR: Query Design for Transformer-Based Object Detection](https://mlsanity.com/paper/2109.07107/) (2021)
- [Deep Vectorization of Technical Drawings](https://mlsanity.com/paper/2003.05471/) (2020)
- [docExtractor: An off-the-shelf historical document element extraction](https://mlsanity.com/paper/2012.08191/) (2020)
- [Vectorization of Line Drawings via PolyVector Fields](https://mlsanity.com/paper/1801.01922/) (2018)
- [Abstracting Sketches through Simple Primitives](https://mlsanity.com/paper/2207.13543/) (2022)
- [DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces](https://mlsanity.com/paper/1901.03781/) (2019)
- [Versailles-FP dataset: Wall Detection in Ancient](https://mlsanity.com/paper/2103.08064/) (2021)
- [PPI-NET: End-to-End Parametric Primitive Inference](https://mlsanity.com/paper/2308.01521/) (2023)

## Built on by (most cited first, 2 of 2)

- [Slow Perception: Let's Perceive Geometric Figures Step-by-step](https://mlsanity.com/paper/2412.20631/) (2024)
- [Text region detection in historical astronomical diagrams](https://mlsanity.com/paper/2606.15886/) (2026)

## Abstract (arXiv)

Automatically extracting the geometric content from the hundreds of thousands of diagrams drawn in historical manuscripts would enable historians to study the diffusion of astronomical knowledge on a global scale. However, state-of-the-art vectorization methods, often designed to tackle modern data, are not adapted to the complexity and diversity of historical astronomical diagrams. Our contribution is thus twofold. First, we introduce a unique dataset of 303 astronomical diagrams from diverse traditions, ranging from the XIIth to the XVIIIth century, annotated with more than 3000 line segments, circles and arcs. Second, we develop a model that builds on DINO-DETR to enable the prediction of multiple geometric primitives. We show that it can be trained solely on synthetic data and accurately predict primitives on our challenging dataset. Our approach widely improves over the LETR baseline, which is restricted to lines, by introducing a meaningful parametrization for multiple primitives, jointly training for detection and parameter refinement, using deformable attention and training on rich synthetic data. Our dataset and code are available on our webpage.