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

TL;DR

This paper introduces a real-time capable video denoising network that uses a gated recurrent Transformer with multiple fusion strategies, achieving state-of-the-art performance with only a one-frame delay.

Contribution

The paper presents a novel multi-fusion gated recurrent Transformer network (GRTN) that reduces delay to one frame while maintaining high denoising quality, incorporating a residual simplified Swin Transformer for attention.

Findings

Achieves SOTA denoising performance with single-frame delay

Uses residual simplified Swin Transformer for robust attention

Outperforms existing multi-frame delay methods in quality

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.