RealVSR
The RealVSR dataset is a benchmark dataset for real-world video super-resolution, containing low-quality and high-resolution video sequences in various formats, used for evaluating and training video super-resolution algorithms.
Dataset description and usage context
Dataset Overview
Dataset Name
RealVSR
Dataset Description
RealVSR is a benchmark dataset for video super-resolution research. The dataset contains high-quality (HR) and low-quality (LR) video sequences, suitable for training and testing video super-resolution models.
Dataset Structure
The dataset includes the following files:
| File | Description |
|---|---|
| GT.zip | All high-quality RGB format sequences |
| LQ.zip | All low-quality RGB format sequences |
| GT_YCbCr.zip | All high-quality YCbCr format sequences |
| LQ_YCbCr.zip | All low-quality YCbCr format sequences |
| GT_test.zip | High-quality RGB format test sequences |
| LQ_test.zip | Low-quality RGB format test sequences |
| GT_YCbCr_test.zip | High-quality YCbCr format test sequences |
| LQ_YCbCr_test.zip | Low-quality YCbCr format test sequences |
| videos.zip | Original videos, containing over 500 LR‑HR video pairs |
Dataset Storage Location
The dataset is stored on Google Drive and Baidu Drive.
Dataset Samples
Sample images of the dataset illustrate several scenes and can be used to preview the dataset contents.
Dataset License
The dataset follows the Apache 2.0 license.
Pair the dataset with AI analysis and content workflows.
Once the source passes your review, move straight into summarization, transformation, report drafting, or presentation generation with the JuheAI toolchain.