Layers, loss functions, datasets, and models for Single Image Super-Resolution (SISR)

[mihirparadkar]

Short Description
Single-Image Super-Resolution describes the domain of enhancing image resolution for single images (as opposed to groups of images of a scene, for example). Solutions in this domain have applications in security, medical imaging, segmentation, and video enhancement.

Papers
Survey paper (2021): From Beginner to Master: A Survey for Deep
Learning-based Single-Image Super-Resolution

Datasets:
Berkeley Segmentation Data Set and Benchmarks 500 (BSDS500)

NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study
Div2K Dataset

Layers
Sub-pixel convolution: Real-Time Single Image and Video Super-Resolution Using an Efficient
Sub-Pixel Convolutional Neural Network

Loss Functions
Gradient Prior Loss
Edge Prior Loss

Metrics
Peak Signal-to-Noise Ratio (PSNR)
Structural Similarity index measure (SSIM)

Existing Implementations
https://keras.io/examples/vision/super_resolution_sub_pixel/
https://github.com/krasserm/super-resolution

[AnimeshMaheshwari22]

Hi. Are we taking this task? Would like to contribute.

[github-actions]

This issue is stale because it has been open for 180 days with no activity. It will be closed if no further activity occurs. Thank you.

[sachinprasadhs]

Thanks for reporting the issue! We have consolidated the development of KerasCV into the new KerasHub package, which supports image, text, and multi-modal models. Please read keras-team/keras-hub#1831. KerasHub will support all the core functionality of KerasCV.

KerasHub can be installed with !pip install -U keras-hub. Documentation and guides are available at keras.io/keras_hub.

With our focus shifted to KerasHub, we are not planning any further development or releases in KerasCV. If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file an issue with KerasHub.