Overview
FMA-Net is a novel framework for joint video super-resolution and deblurring, leveraging flow-guided dynamic filtering and iterative feature refinement with multi-attention to restore clean high-resolution videos from blurry low-resolution ones.
Flow-Guided Dynamic Filtering
Enables precise estimation of spatio-temporally-variant degradation and restoration kernels through sophisticated motion representation learning.
Iterative Feature Refinement with Multi-Attention
Refines features in a course-to-fine manner through iterative updates, leveraging multi-attention to anchor and sharpen features temporally.
Temporal Anchor Loss
Temporally anchors and sharpens features, enabling effective feature refinement and restoration.
Stacked FRMA Blocks
Trained with the novel temporal anchor loss, these blocks enable iterative feature refinement and restoration.
Get started
- Open the official website and confirm the service is available in your region.
- Check the current plan, usage limits and terms for your intended use.
- Try a small task with sample data before committing to a paid plan.
Editorial note
Pricing checked: Sep 20, 2026. Tiered plans available. Review current pricing and subscription options on the official website.
Record updated: Sep 20, 2026
Suggest a correction
