FMA-Net icon indicating copy to clipboard operation
FMA-Net copied to clipboard

verified publisher icon KAIST-VICLab
→

Metadata

[CVPR 2024 Oral] Official repository of FMA-Net

FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring

†Co-corresponding authors
1Korea Advanced Institute of Science and Technology, South Korea
2Chung-Ang University, South Korea

This repository is the official PyTorch implementation of "FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring". FMA-Net achieves state-of-the-art performance in joint video super-resolution and deblurring (VSRDB).

Please visit our project page for more visual results.

🎬 Network Architecture

overall_structure

Codes and pretrained models will be updated soon.

← Metadata

542
Stars
31
Forks
Watchers

Owner

verified publisher icon KAIST-VICLab

Metadata

[CVPR 2024 Oral] Official repository of FMA-Net

Back