# From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding

arXiv: https://arxiv.org/abs/2602.07645 · HTML: https://mlsanity.com/paper/2602.07645/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 7 Feb 2026.

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

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [Nougat: Neural Optical Understanding for Academic Documents](https://mlsanity.com/paper/2308.13418/) (2023)
- [mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding](https://mlsanity.com/paper/2403.12895/) (2024)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning](https://mlsanity.com/paper/2305.14761/) (2023)
- [Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering](https://mlsanity.com/paper/2403.03163/) (2024)
- [Unifying Vision, Text, and Layout for Universal Document Processing](https://mlsanity.com/paper/2212.02623/) (2022)
- [MatCha: Enhancing Visual Language Pretraining with Math Reasoning and Chart Derendering](https://mlsanity.com/paper/2212.09662/) (2022)
- [ScreenAI: A Vision-Language Model for UI and Infographics Understanding](https://mlsanity.com/paper/2402.04615/) (2024)
- [DocVLM: Make Your VLM an Efficient Reader](https://mlsanity.com/paper/2412.08746/) (2024)
- [ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules](https://mlsanity.com/paper/2304.02173/) (2023)
- [MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding](https://mlsanity.com/paper/2410.21311/) (2024)
- [DLAFormer: An End-to-End Transformer For Document Layout Analysis](https://mlsanity.com/paper/2405.11757/) (2024)

## Built on by (most cited first, 1 of 1)

- [DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable](https://mlsanity.com/paper/2608.00548/) (2026)

## Abstract (arXiv)

Infographics are widely used to communicate information with a combination of text, icons, and data visualizations, but once exported as images their content is locked into pixels, making updates, localization, and reuse expensive. We describe textscImages2Slides, an API-based pipeline that converts a static infographic (PNG/JPG) into a native, editable Google Slides slide by extracting a region-level specification with a vision-language model (VLM), mapping pixel geometry into slide coordinates, and recreating elements using the Google Slides batch update API. The system is model-agnostic and supports multiple VLM backends via a common JSON region schema and deterministic postprocessing. On a controlled benchmark of 29 programmatically generated infographic slides with known ground-truth regions, textscImages2Slides achieves an overall element recovery rate of 0.989±0.057 (text: 0.985±0.083, images: 1.000±0.000), with mean text transcription error CER=0.033±0.149 and mean layout fidelity IoU=0.364±0.161 for text regions and 0.644±0.131 for image regions. We also highlight practical engineering challenges in reconstruction, including text size calibration and non-uniform backgrounds, and describe failure modes that guide future work.