6 datasets found

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

A video restoration dataset using enhanced deformable convolutional networks.

A benchmark dataset for low-light video enhancement.

A novel low-light video dataset, consisting of 40 scenes with various motion scenarios under two distinct low-lighting conditions, incorporating genuine noise and temporal...

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...

Video enhancement with task-oriented flow.