18 datasets found

The DAVIS-10 dataset is a benchmark for video super-resolution.

Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR)...

Video super-resolution paradigm, combining semantic priors with pixel-level features

The SPMCS dataset is a video dataset for detail-revealing video super-resolution tasks.

The HDRTV1K dataset, which contains 4K SDR frames and 4K HDR frames pairs.

The 4K HDR dataset collected and produced by Kim et al. [1], [5]. They gathered 4K HDR videos and their corresponding 4K SDR videos from YouTube.

Video super-resolution (VSR) is the technique of increasing the nominal resolution of image/video content accompanied with quality improvement.

The dataset used for testing the AniTalker framework, containing 4,242 unique speaker IDs, 17,108 video clips, and a cumulative duration of 55 hours.

The proposed group-based bi-directional recurrent wavelet neural networks (GBR-WNN) for Video Super-Resolution.

Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using...

RealMCVSR dataset is a video super-resolution dataset containing ultra-wide, wide-angle, and telephoto videos from multiple scenes.

Video super-resolution (VSR) aims to restore a photo-realistic high-resolution (HR) video frame from both its corresponding low-resolution (LR) frame (reference frame) and...

Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also...

The Vid4 dataset is a video super-resolution dataset, which consists of 4 videos of resolution 640 x 480.

The REDS dataset is a video super-resolution dataset, which consists of 240 videos of resolution 720 x 1280 captured by GoPro. Each video consists of 100 HR frames.

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 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...

RealBasicVSR dataset is used for upscaling the generated videos.