21 datasets found

The AOM CTC Class A1 dataset is a high-resolution video dataset used for evaluating the performance of video compression algorithms.

A video compression degradation model to synthesize low-resolution image data in the blind SISR task.

The dataset used for training and testing the proposed DNN-based frame prediction architecture.

The proposed DNN-based frame prediction architecture that is able to support both uni- and bi-directional prediction.

The dataset used in the paper is the UVG dataset, which contains 7 1080p video sequences and a total of 3900 frames.

A learning-based video compression method

A learning-based video compression method

A video quality assessment dataset based on JND measurement, containing 1509 videos.

A video compression framework that performs all operations in the feature space

A dataset of images and videos for video compression research.

The proposed multi-density attention network for loop filtering in video compression.

Video compression is a basic requirement for consumer and professional video applications alike. Video coding standards such as H.264/AVC and H.265/HEVC are widely deployed in...

The dataset used in the paper is a collection of video sequences with varying resolutions and bit depths, used for training and testing the proposed video compression framework.

The dataset used in the paper is a collection of video sequences with varying resolutions and bit depths, used for training and testing the proposed video compression framework.

The UVG dataset comprises 16 video sequences of 3840×2160, recorded at 120 frames per second.

The dataset used in the paper is a 360o video dataset, which is used to evaluate the performance of the proposed distortion-aware loop filtering model.

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 non-local adaptive loop filter for HEVC.

The proposed RHCNN model for in-loop filtering in HEVC.

The proposed MIF approach enhances the quality of each encoded frame leveraging multiple adjacent frames.