computer-vision

Reference-based Super-Resolution

3260 papers • 126 benchmarks • 313 datasets

Reference-based Super-Resolution aims to recover high-resolution images by utilizing external reference images containing similar content to generate rich textures.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in reference-based-super-resolution

Trend

Dataset

Best Model

Actions

CUFED5 - 4x upscaling

Libraries

i

Use these libraries to find reference-based-super-resolution models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Image Super-Resolution by Neural Texture Transfer

Zhe L. Lin, Zhaowen Wang, Zhifei Zhang, H. Qi•Sat Mar 02 2019

An end-to-end deep model which enriches HR details by adaptively transferring the texture from Ref images according to their textural similarity is designed, which facilitates multi-scale neural transfer that allows the model to benefit more from those semantically related Ref patches, and gracefully degrade to SISR performance on the least relevant Ref inputs.

323

Content

0

Paper Graph

Dual-Camera Super-Resolution with Aligned Attention Modules

Qifeng Chen, Qiong Yan, Wenxiu Sun, Tengfei Wang, Jiaxin Xie•Thu Sep 02 2021

This work proposes a self-supervised domain adaptation strategy for real-world images that generalizes the standard patch-based feature matching with spatial alignment operations and further explores the dual-camera super-resolution that is one promising application of RefSR.

56 0

Paper Graph

Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations

W. Zuo, Yunjin Chen, Hongzhi Zhang, Zhilu Zhang, Ruohao Wang•Tue Mar 01 2022

This paper presents a novel self-supervised learning approach for real-world image SR from observations at dual camera zooms (SelfDZSR), and takes the telephoto image instead of an additional high-resolution image as the supervision information and select a center patch from it as the reference to super-resolve the corresponding short-focus image patch.

28 0

Paper Graph

CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping

Lu Fang, Yebin Liu, Haitian Zheng, Mengqi Ji, Haoqian Wang•Thu Jul 26 2018

Using cross-scale warping, the CrossNet network is able to perform spatial alignment at pixel-level in an end-to-end fashion, which improves the existing schemes both in precision and efficiency.

224 0

Paper Graph

Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution

I. Kweon, Jinsun Park, Gyumin Shim•Sun May 31 2020

In this paper, we propose a novel and efficient reference feature extraction module referred to as the Similarity Search and Extraction Network (SSEN) for reference-based super-resolution (RefSR) tasks. The proposed module extracts aligned relevant features from a reference image to increase the performance over single image super-resolution (SISR) methods. In contrast to conventional algorithms which utilize brute-force searches or optical flow estimations, the proposed algorithm is end-to-end trainable without any additional supervision or heavy computation, predicting the best match with a single network forward operation. Moreover, the proposed module is aware of not only the best matching position but also the relevancy of the best match. This makes our algorithm substantially robust when irrelevant reference images are given, overcoming the major cause of the performance degradation when using existing RefSR methods. Furthermore, our module can be utilized for self-similarity SR if no reference image is available. Experimental results demonstrate the superior performance of the proposed algorithm compared to previous works both quantitatively and qualitatively.

107 0

Paper Graph

Robust Reference-based Super-Resolution via C2-Matching

Ziwei Liu, Chen Change Loy, Kelvin C. K. Chan, Yuming Jiang•Mon May 31 2021

The proposed C2-Matching significantly outperforms state of the arts by over 1dB on the standard CUFED5 benchmark and shows great generalizability on WR-SR dataset as well as robustness across large scale and rotation transformations.

118 0

Paper Graph

Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution

Wenming Yang, Yapeng Tian, Q. Liao, Jie Zhou, Bin Xia, Yucheng Hang•Tue Jan 11 2022

An Accelerated Multi-scale Aggregation network (AMSA) for Reference-based Super-Resolution, including Coarse-to-Fine Embedded PatchMatch (CFE-PatchMatch) and Multi-Scale Dynamic Aggregation (MSDA) module is proposed and Experimental results show that the proposed AMSA achieves superior performance over state-of-the-art approaches on both quantitative and qualitative evaluations.

32 0

Paper Graph

Self-Supervised Learning for Real-World Super-Resolution From Dual and Multiple Zoomed Observations

Wangmeng Zuo, Zhilu Zhang, Ruohao Wang, Hongzhi Zhang•Tue Mar 19 2024

A novel self-supervised learning approach for real-world RefSR from observations at dual and multiple camera zooms is proposed, including patch-based optical flow alignment and auxiliary-LR guiding alignment and local overlapped sliced Wasserstein loss.

5 0

Paper Graph

Reference-based Image Super-Resolution with Deformable Attention Transformer

K. Zhang, Wenguan Wang, Jingyun Liang, Jiezhang Cao, Yawei Li, Yulun Zhang, Luc Van Goo•Sun Jul 24 2022

A deformable attention Transformer, namely DATSR, with multiple scales, each of which consists of a texture feature encoder (TFE) module, a reference-based deformable Attention (RDA) module and a residual feature aggregation (RFA) module is proposed.

92 0

Paper Graph

HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area Surveillance

H. F. Ates, B. Gunturk, H. U. Suluhan•Fri Apr 08 2022

This paper proposes an end-to-end trainable deep network that performs optical flow estimation and frame reconstruction by combining inputs from both video feeds and provides significant improvement over existing video frame interpolation and RefSR techniques in terms of objective PSNR and SSIM metrics.

0 0

Paper Graph

Adding a benchmark result helps the community track progress.