ChartLens：用于图表数据校正和事实性摘要精炼的双分支框架
ChartLens: A Dual-Branch Framework for Chart Data Correction and Factual Summary Refinement
AI总结：
提出ChartLens双分支框架，通过结构感知CSV验证校正和文本保留引导的摘要精炼，提升图表数据恢复与摘要事实性，在DataMFM挑战赛Track 2中获第一。
摘要：
在本报告中，我们展示了针对DataMFM挑战赛Track 2：图表理解（Chart Understanding）的冠军解决方案。该赛道要求模型从图表图像中恢复结构化图表数据并生成忠实于事实的自然语言摘要。为了满足准确数据提取和事实性叙述的互补需求，我们提出了ChartLens，一个用于图表数据校正和摘要精炼的双分支框架。ChartLens由两个关键模块组成：结构感知CSV验证与校正（SAVC）和文本保留引导的摘要精炼（TRSR）。SAVC通过验证和校正提高结构化数据提取的可靠性，而TRSR通过保留图表中的关键文本和数值证据来增强摘要生成。通过结合模型自适应、基于校正的生成和OCR辅助的证据依据，ChartLens改善了结构化数据恢复和摘要事实性。在测试集上，我们的最终系统获得了69.10的总分，并在Track 2中排名第一，证明了其在准确图表理解方面的有效性。我们的代码将在以下网址发布：this https URL。
英文摘要：
In this report, we present our champion solution for the DataMFM Challenge Track 2: Chart Understanding. This track requires models to recover structured chart data and generate faithful natural-language summaries from chart images. To address the complementary requirements of accurate data extraction and factual narration, we propose ChartLens, a dual-branch framework for chart data correction and summary refinement. ChartLens consists of two key modules: Structure-Aware CSV Verification and Correction (SAVC) and Text-Retention-Guided Summary Refinement (TRSR). SAVC improves the reliability of structured data extraction through verification and correction, while TRSR enhances summary generation by preserving critical textual and numerical evidence from charts. By combining model adaptation, correction-based generation, and OCR-assisted evidence grounding, ChartLens improves both structured data recovery and summary factuality. On the test set, our final system achieves an overall score of 69.10 and ranks first in Track 2, demonstrating its effectiveness for accurate chart understanding. Our code will be released at: https://github.com/iLearn-Lab/CVPRW26-ChartLens.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
