# RectiNet-v2: A stacked network architecture for document image dewarping

arXiv: https://arxiv.org/abs/2102.01120 · HTML: https://mlsanity.com/paper/2102.01120/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 6 of 6)

- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation](https://mlsanity.com/paper/1902.04049/) (2019)
- [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://mlsanity.com/paper/1907.05740/) (2019)
- [Multiview Rectification of Folded Documents](https://mlsanity.com/paper/1606.00166/) (2016)
- [Can You Read Me Now? Content Aware Rectification using Angle Supervision](https://mlsanity.com/paper/2008.02231/) (2020)
- [A Gated and Bifurcated Stacked U-Net Module for Document Image Dewarping](https://mlsanity.com/paper/2007.09824/) (2020)

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

- [Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification](https://mlsanity.com/paper/2210.05954/) (2022)

## Abstract (arXiv)

With the advent of mobile and hand-held cameras, document images have found their way into almost every domain. Dewarping of these images for the removal of perspective distortions and folds is essential so that they can be understood by document recognition algorithms. For this, we propose an end-to-end CNN architecture that can produce distortion free document images from warped documents it takes as input. We train this model on warped document images simulated synthetically to compensate for lack of enough natural data. Our method is novel in the use of a bifurcated decoder with shared weights to prevent intermingling of grid coordinates, in the use of residual networks in the U-Net skip connections to allow flow of data from different receptive fields in the model, and in the use of a gated network to help the model focus on structure and line level detail of the document image. We evaluate our method on the DocUNet dataset, a benchmark in this domain, and obtain results comparable to state-of-the-art methods.