Reference-based Super-Resolution
13 papers with code • 1 benchmarks • 0 datasets
Reference-based Super-Resolution aims to recover high-resolution images by utilizing external reference images containing similar content to generate rich textures.
Benchmarks
These leaderboards are used to track progress in Reference-based Super-Resolution
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Most implemented papers
Image Super-Resolution by Neural Texture Transfer
ZZUTK/SRNTT
•
•
CVPR 2019
Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given.
Dual-Camera Super-Resolution with Aligned Attention Modules
Tengfei-Wang/DualCameraSR
•
•
ICCV 2021
We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR), which utilizes reference images for high-quality and high-fidelity results.
CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping
htzheng/ECCV2018_CrossNet_RefSR
•
•
ECCV 2018
The Reference-based Super-resolution (RefSR) super-resolves a low-resolution (LR) image given an external high-resolution (HR) reference image, where the reference image and LR image share similar viewpoint but with significant resolution gap x8.
Robust Reference-Based Super-Resolution With Similarity-Aware Deformable Convolution
Slime0519/CVPR_2020_SSEN
•
•
CVPR 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.
Robust Reference-based Super-Resolution via C2-Matching
yumingj/C2-Matching
•
•
CVPR 2021
However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e. g. scale and rotation) and the resolution gap (e. g. HR and LR).
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution
zj-binxia/amsa
•
•
To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size.
Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations
For this purpose, we take 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.
HSTR-Net: High Spatio-Temporal Resolution Video Generation For Wide Area Surveillance
umutsuluhan/HSTRNet-Interp
•
•
Wide area surveillance has many applications and tracking of objects under observation is an important task, which often needs high spatio-temporal resolution (HSTR) video for better precision.
Reference-based Image Super-Resolution with Deformable Attention Transformer
Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images.
Reference-based Image and Video Super-Resolution via C2-Matching
To tackle these challenges, we propose C2-Matching in this work, which performs explicit robust matching crossing transformation and resolution.
