CVNov 26, 2018

Deep Laplacian Pyramid Network for Text Images Super-Resolution

arXiv:1811.10449v136 citations
Originality Synthesis-oriented
AI Analysis

This work addresses super-resolution for text images, which is an incremental improvement over existing methods for natural images.

The paper tackled single text image super-resolution by adapting a deep network from natural images and combining Gradient Difference Loss with L1/L2 loss to enhance edges, resulting in improved super-resolution outcomes as shown in quantitative and qualitative evaluations on their dataset.

Convolutional neural networks have recently demonstrated interesting results for single image super-resolution. However, these networks were trained to deal with super-resolution problem on natural images. In this paper, we adapt a deep network, which was proposed for natural images superresolution, to single text image super-resolution. To evaluate the network, we present our database for single text image super-resolution. Moreover, we propose to combine Gradient Difference Loss (GDL) with L1/L2 loss to enhance edges in super-resolution image. Quantitative and qualitative evaluations on our dataset show that adding the GDL improves the super-resolution results.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes