Loading [MathJax]/extensions/MathMenu.js
A Practical Gated Recurrent Transformer Network Incorporating Multiple Fusions for Video Denoising | IEEE Conference Publication | IEEE Xplore

A Practical Gated Recurrent Transformer Network Incorporating Multiple Fusions for Video Denoising


Abstract:

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impra...Show More

Abstract:

State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous denoising mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose a multi-fusion gated recurrent Transformer network (GRTN) that achieves SOTA denoising performance with only a single-frame delay. Specifically, the spatial denoising module extracts features from the current frame, while the reset gate selects relevant information from the previous frame and fuses it with current frame features via the temporal denoising module. The update gate then further blends this result with the previous frame features, and the reconstruction module integrates it with the current frame. To robustly compute attention for noisy features, we propose a residual simplified Swin Transformer with Euclidean distance (RSSTE) in the spatial and temporal denoising modules. Comparative objective and subjective results show that our GRTN achieves denoising performance comparable to SOTA multi-frame delay networks, with only a single-frame delay.
Date of Conference: 06-11 April 2025
Date Added to IEEE Xplore: 07 March 2025
ISBN Information:

ISSN Information:

Conference Location: Hyderabad, India

References

References is not available for this document.