DocTr

DocTr copied to clipboard

Hello, 1: when are you going to open source training? 2: How fast is your plan? 3: What is used in the document detection of your scheme and how is the effect

Hi, thanks for your attention to our work. 1&2. We will open the source code when our another work DocScanner is accepted. 3. I do not quite understand the third question.

How is your docscanner implemented? Can you give us a general idea? Semantic or instance segmentation or key point detection?

You can refer to the paper for details. https://arxiv.org/pdf/2110.14968.pdf