# The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution

arXiv: https://arxiv.org/abs/1808.00043 · HTML: https://mlsanity.com/paper/1808.00043/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 8 of 8)

- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors](https://mlsanity.com/paper/2304.03994/) (2023)
- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [Debiased Subjective Assessment of Real-World Image Enhancement](https://mlsanity.com/paper/2106.10080/) (2021)
- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [Error-Aware Spatial Ensembles for Video Frame Interpolation](https://mlsanity.com/paper/2207.12305/) (2022)
- [Degradation-Agnostic Statistical Facial Feature Transformation for Blind Face Restoration in Adverse Weather Conditions](https://mlsanity.com/paper/2507.07464/) (2025)

## Abstract (arXiv)

While implicit generative models such as GANs have shown impressive results in high quality image reconstruction and manipulation using a combination of various losses, we consider a simpler approach leading to surprisingly strong results. We show that texture loss alone allows the generation of perceptually high quality images. We provide a better understanding of texture constraining mechanism and develop a novel semantically guided texture constraining method for further improvement. Using a recently developed perceptual metric employing "deep features" and termed LPIPS, the method obtains state-of-the-art results. Moreover, we show that a texture representation of those deep features better capture the perceptual quality of an image than the original deep features. Using texture information, off-the-shelf deep classification networks (without training) perform as well as the best performing (tuned and calibrated) LPIPS metrics. The code is publicly available.