TSFormer: A Robust Framework for Efficient UHD Image Restoration
This addresses the practical deployment challenge for applications requiring high visual fidelity in UHD image restoration, though it appears incremental as it builds on existing methods with a novel integration.
The paper tackles the trade-off between restoration quality and efficiency in ultra-high-definition image restoration by proposing TSFormer, which integrates trusted learning with sparsification to achieve state-of-the-art quality while running 4K images at 40fps with 3.38 M parameters.
Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \textbf{T}rusted learning with \textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with random matrix theory to quantify the uncertainty of tokens, thereby improving the robustness of the model. Our model can run a 4K image in real time (40fps) with 3.38 M parameters. Extensive experiments demonstrate that TSFormer achieves state-of-the-art restoration quality while enhancing generalization and reducing computational demands. In addition, our token filtering method can be applied to other image restoration models to effectively accelerate inference and maintain performance.