FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising

TL;DR

The paper introduces FFDNet, a fast and flexible CNN-based image denoising method that handles various noise levels and spatially variant noise with a single model, outperforming traditional methods in speed and effectiveness.

Contribution

It proposes a novel CNN architecture with a tunable noise level map, enabling effective denoising across multiple noise levels and spatial variations with a single model.

Findings

Handles a wide range of noise levels with one network

Effective removal of spatially variant noise

Faster than BM3D without performance loss

Abstract

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we present a fast and flexible denoising convolutional neural network, namely FFDNet, with a tunable noise level map as the input. The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing discriminative denoisers, FFDNet enjoys several desirable properties, including (i) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network, (ii) the ability to remove spatially variant noise by specifying a non-uniform noise level map, and (iii) faster speed than benchmark BM3D even on CPU without sacrificing denoising performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate FFDNet in comparison with state-of-the-art denoisers. The results show that FFDNet is effective and efficient, making it highly attractive for practical denoising applications.