Edge-Informed Single Image Super-Resolution

Kamyar Nazeri, Harrish Thasarathan, Mehran Ebrahimi
9/11/2019
eess.IVcs.CV

Official code: knazeri/edge-informed-sisr (80 stars, last commit 2020-02-11).

Abstract

The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR problem is reformulated as an image inpainting task. We use a two-stage inpainting model as a baseline for super-resolution and show its effectiveness for different scale factors (x2, x4, x8) compared to basic interpolation schemes. This model is trained using a joint optimization of image contents (texture and color) and structures (edges). Quantitative and qualitative comparisons are included and the proposed model is compared with current state-of-the-art techniques. We show that our method of decoupling structure and texture reconstruction improves the quality of the final reconstructed high-resolution image. Code and models available at: https://github.com/knazeri/edge-informed-sisr

View on arXivView PDF

Code Implementations(1)

knazeri/edge-informed-sisrOfficial100%

Edge-Informed Single Image Super-Resolution, ICCVW 2019 https://arxiv.org/abs/1909.05305

8020PythonAug 28, 20196 years agoNOASSERTION

Similar Papers

RETHINED: A New Benchmark and Baseline for Real-Time High-Resolution Image Inpainting On Edge Devices

84% match2025

EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning

83% match1 repo2.6k2019

Ultra High-Resolution Image Inpainting with Patch-Based Content Consistency Adapter

83% match1 repo112025

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

83% match1 repo8.1k2020

Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model

82% match2026

Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting

82% match1 repo4002020

Cite this paper

@article{nazeri2019edgeinformed,
  title  = {Edge-Informed Single Image Super-Resolution},
  author = {Kamyar Nazeri and Harrish Thasarathan and Mehran Ebrahimi},
  year   = {2019},
  eprint = {1909.05305},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1909.05305}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1909.05305.svg)](https://codeofpaper.com/paper/1909.05305)

Discussion