17 datasets found

The dataset used in the paper is for image deblurring, and it is compared with different methods such as PnP-ADMM and PnP-FISTA.

The CU-Mamba model is used for image restoration, and the authors tested it on the SIDD and DND datasets.

The commonly used benchmark for image deblurring is Go-Pro (Nah, Kim, and Lee 2017), where the input blurry images are synthetic.

Image deblurring task is an ill-posed one, where exists infinite feasible solutions for blurry image. Modern deep learning approaches usually discard the learning of blur kernels...

The dataset used in this paper for Ring Deconvolution Microscopy (RDM) experiments.

The Canon dual-pixel defocus dataset contains 1000 pairs of sharp and blurry 6720×4480 images.

The GoPro motion deblurring dataset contains 3214 pairs of clean and blurry 1280 × 720 images.

The Kohler dataset is a benchmark for blind image deblurring, containing 4 images with 12 different kernels.

The GoPro dataset is used for training, which contains 2103 pairs of blurred clear control images. The validation set used for training is 460 pairs of randomly divided images....

The CelebAHQ dataset was used with a Gaussian blur kernel with an std. of 2 [11].

Deblur-Test dataset for image deblurring

Real-world blur dataset for learning and benchmarking deblurring algorithms.

The dataset used in the paper for image deblurring tasks.

The RealBlur test dataset for image deblurring.

The HIDE test dataset for image deblurring.

The GoPro test dataset for image deblurring.

The dataset used in the paper is YFCC100M, a large-scale video dataset. The dataset is used for foreground and background patch extraction and object recognition tasks.