DocEnTr: An End-to-End Document Image Enhancement Transformer
This addresses the need for improved digitization and processing of documents, though it appears incremental as it builds on transformer methods for a specific domain.
The paper tackles the problem of enhancing degraded document images, such as machine-printed and handwritten ones, by proposing an end-to-end vision transformer architecture that achieves state-of-the-art performance on DIBCO benchmarks.
Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: \url{https://github.com/dali92002/DocEnTR}.