The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality
Computer Graphics Forum · 17.06.2026
DOI: 10.1111/cgf.70447 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 17.06.2026. Verfasst von Roxana Bujack und 4 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one‐shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs. Human evaluation, though effective, is costly and impractical at scale. To alleviate this problem, we propose an automated metric that evaluates visualization quality without relying on extensive human‐labeled datasets. Instead, our approach uses the original underlying data as implicit ground truth. Specifically, we introduce a method that measures visualization quality by assessing the reconstruction accuracy of the original data from the visualization itself. This reconstruction‐based metric provides an autonomous and scalable proxy for thorough human evaluation, facilitating more efficient and reliable AI‐driven visualization workflows.
Zitieren
APA
Bujack, R., Lo, L., Stam, E., Biswas, A., & Rogers, D. (2026). The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality. Computer Graphics Forum. https://doi.org/10.1111/cgf.70447
Vancouver
Bujack R, Lo L, Stam E, Biswas A, Rogers D. The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality. Computer Graphics Forum. 2026. doi:10.1111/cgf.70447
BibTeX
@article{Bujack2026,
author = {Bujack, Roxana and Lo, Li‐Ta and Stam, Ethan and Biswas, Ayan and Rogers, David},
title = {The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70447}
}
EUVIMED