Nan Xue, Gui-Song Xia, Rujiao Long, Zhibo Yang, Cong Yao, Xiangwei Jiang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
This paper addresses the problem of document image dewarping, which aims at eliminating the geometric distortion in document images for document digitization. Instead of designing a better neural network to approximate the optical flow fields between the inputs and outputs, we pursue the best readability by taking the text lines and the document boundaries into account from a constrained optimization perspective. Specifically, our proposed method first learns the boundary points and the pixels in the text lines and then follows the most simple observation that the boundaries and text lines in both horizontal and vertical directions should be kept after dewarping to introduce a novel grid regularization scheme. To obtain the final forward mapping for dewarping, we solve an optimization problem with our proposed grid regularization. The experiments comprehensively demonstrate that our proposed approach outperforms the prior arts by large margins in terms of readability (with the metrics of Character Errors Rate and the Edit Distance) while maintaining the best image quality on the publiclyavailable DocUNet benchmark.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.16850")
get_code_for_paper("2203.16850")
have("2203.16850")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.16850.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.16850)
Connect an agent — have() is free.