Image Super-Resolution Models
ClassSR
Introduced by Kong et al. in ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data CharacteristicClassSR is a framework to accelerate super-resolution (SR) networks on large images (2K-8K). ClassSR combines classification and SR in a unified framework. In particular, it first uses a Class-Module to classify the sub-images into different classes according to restoration difficulties, then applies an SR-Module to perform SR for different classes. The Class-Module is a conventional classification network, while the SR-Module is a network container that consists of the to-be-accelerated SR network and its simplified versions.
Source: ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Classification | 1 | 33.33% |
| General Classification | 1 | 33.33% |
| Super-Resolution | 1 | 33.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
