JingyunLiang/RVRT
Recurrent Video Restoration Transformer with guided deformable attention for video super-resolution, deblurring, and denoising.
Not currently ranked — collecting fresh signals.
star history
RVRT is a transformer-based architecture published at NeurIPS 2022 that addresses low-level video processing tasks including super-resolution, deblurring, and denoising. The model employs guided deformable attention mechanisms and recurrent structures to process video frames efficiently while maintaining temporal consistency. It provides pretrained models and achieves state-of-the-art results on standard benchmarks including REDS, Vimeo90K, GoPro, and DAVIS datasets.
Frequently asked
- What is JingyunLiang/RVRT?
- Recurrent Video Restoration Transformer with guided deformable attention for video super-resolution, deblurring, and denoising.
- Is RVRT open source?
- Yes — JingyunLiang/RVRT is an open-source project tracked on heatdrop.
- What language is RVRT written in?
- JingyunLiang/RVRT is primarily written in Python.
- How popular is RVRT?
- JingyunLiang/RVRT has 448 stars on GitHub.
- Where can I find RVRT?
- JingyunLiang/RVRT is on GitHub at https://github.com/JingyunLiang/RVRT.