microsoft / unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
https://aka.ms/GeneralAI
MIT License
19.63k stars 2.51k forks source link

How to detect the reading order of layout result? #1160

Open lycfight opened 1 year ago

lycfight commented 1 year ago

Describe Model I am using (UniLM, MiniLM, LayoutLM ...): I got the result of layout analysis through layoutlmv3, but the order of blocks of the result is random. Can I get the reading order of block granularity through LayoutReader?

sebastianfernandezgarcia commented 4 months ago

Have you found a solution? I got the bounding boxes with DiT/LayoutLMv3 but now i need to order them. Some times are just straight top down format. But sometimes there are different layouts and i want to order them correctly