JingyunLiang/VRT
A video restoration transformer for enhancing video quality through super-resolution, deblurring, and denoising.
Not currently ranked — collecting fresh signals.
star history
VRT is a transformer-based architecture for video restoration tasks including super-resolution, deblurring, and denoising. It is implemented in PyTorch and provides pretrained models achieving state-of-the-art performance on benchmarks like REDS, Vimeo90K, and Vid4. The model processes video frames using attention mechanisms to leverage temporal information for high-quality video enhancement.
Frequently asked
- What is JingyunLiang/VRT?
- A video restoration transformer for enhancing video quality through super-resolution, deblurring, and denoising.
- Is VRT open source?
- Yes — JingyunLiang/VRT is an open-source project tracked on heatdrop.
- What language is VRT written in?
- JingyunLiang/VRT is primarily written in Python.
- How popular is VRT?
- JingyunLiang/VRT has 1.5k stars on GitHub.
- Where can I find VRT?
- JingyunLiang/VRT is on GitHub at https://github.com/JingyunLiang/VRT.