Metraipolis › archive › dc_e215c258cb7a
ChartRevive: Reconstructing Data Visualizations from Chart Images Using MLLM — arXiv:2609.27146
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27146
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T10:51:25.553Z
- SHA-256 of the archived text
6e23b1f60353139acd3b094b2af147c223fd26b25a34f0d0141ec6c410f20990- Stable URL of this page
https://metraipolis.com/documento/dc_e215c258cb7a
How to cite
ChartRevive: Reconstructing Data Visualizations from Chart Images Using MLLM — arXiv:2609.27146 — arXiv (en), https://arxiv.org/abs/2609.27146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e215c258cb7a (Metraipolis archive dc_e215c258cb7a, sha256 6e23b1f60353139acd3b094b2af147c223fd26b25a34f0d0141ec6c410f20990)
BibTeX
@misc{dce215c258cb7a,
title = {ChartRevive: Reconstructing Data Visualizations from Chart Images Using MLLM — arXiv:2609.27146},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27146},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e215c258cb7a; sha256 6e23b1f60353139acd3b094b2af147c223fd26b25a34f0d0141ec6c410f20990},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Static chart images are widely used in scientific publications, business reports, and presentations, yet recovering both the underlying data and visual design from chart images remains a labor-intensive manual process, making them difficult to reuse. While prior work has primarily focused on data extraction, the extraction of visual design specifications, including colors, marker shapes, and axis configurations, remains underexplored. To identify a suitable model for chart reconstruction, we systematically benchmark five multimodal large language models (MLLMs) across five basic chart types on both data and design extraction tasks. Our evaluation shows that textual and categorical information can generally be extracted reliably, whereas numeric and spatial information remain challenging. Among the evaluated models, GPT-5.4 achieves the best overall performance and is adopted as the backbone of our system. Guided by these findings, we present ChartRevive, a mixed-initiative system that combines MLLM-based extraction with an interactive verification interface, supporting users to efficiently inspect, correct, and refine reconstructed charts through overlay-based verification and real-time rebuilding. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.27146 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T10:05:38.586Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).