19 datasets found

The dataset used in the paper is a large-scale photo sharing service, where images are stored and retrieved. The authors propose a new recompression technique to reduce storage...

The TECNICK image dataset is a collection of images used for testing image compression algorithms.

The CLIC image dataset is a collection of images used for testing image compression algorithms.

The Kodak PhotoCD image dataset is a collection of images used for testing image compression algorithms.

The proposed JointIQ-Net is a novel end-to-end learning scheme for image compression and quality enhancement.

The dataset used in the paper for neural image compression.

The CIC 2020 dataset is a collection of images with different compression methods.

The dataset used in the paper is not explicitly described. However, it is mentioned that the authors used a transformer-masked autoencoder (TMAE) to enhance data compression in...

Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1...

The dataset used in the paper for neural joint source-channel coding.

The Kodak True Color Image Suite is a dataset of images used for evaluating image compression algorithms.

The dataset used in the paper is the CLIC professional-train dataset, which contains images that are too large to fit into the eight gigabytes memory of Nvidia Geforce GTX1070.

The proposed system is composed of three neural networks (NN): an auto-regressive module (ARM) fψ, an upsampler fυ and a synthesis fθ.

The dataset is a collection of 256x256 pixel images.

The proposed StableVSR is built upon a pre-trained Latent Diffusion Model (LDM) for single image super-resolution (SISR). We use Stable Diffusion ×4 Upscaler (SD×4Upscaler)2. It...

The proposed system is composed of three neural networks (NN): an auto-regressive module (ARM) fψ, an upsampler fυ and a synthesis fθ.

The proposed framework for leveraging the semantic segment without transferring any extra bit.

The proposed deep multiple description coding framework is evaluated on several commonly available datasets, including Set41, McMaster2, Kodak PhotoCD dataset, denoted as...

Single Image Super-Resolution (SR) aims to generate a High Resolution (HR) image I SR from a low resolution (LR) im-age I LR such that it is similar to original HR image I HR....