Feature-Align Network with Knowledge Distillation for Efficient Denoising

TL;DR

This paper introduces an efficient neural network architecture with a novel Feature-Align layer and knowledge distillation techniques, enabling high-quality RAW image denoising on resource-constrained devices like smartphones.

Contribution

The paper presents a new Feature-Align layer, a Feature Matching Loss for knowledge distillation, and empirical analysis of model specialization, advancing efficient denoising for mobile devices.

Findings

Achieves high-quality denoising with significantly fewer parameters and MACs.

Performs competitively with state-of-the-art large networks on benchmark datasets.

Enables model size reduction by trading off memory for compute.

Abstract

We propose an efficient neural network for RAW image denoising. Although neural network-based denoising has been extensively studied for image restoration, little attention has been given to efficient denoising for compute limited and power sensitive devices, such as smartphones and smartwatches. In this paper, we present a novel architecture and a suite of training techniques for high quality denoising in mobile devices. Our work is distinguished by three main contributions. (1) Feature-Align layer that modulates the activations of an encoder-decoder architecture with the input noisy images. The auto modulation layer enforces attention to spatially varying noise that tend to be "washed away" by successive application of convolutions and non-linearity. (2) A novel Feature Matching Loss that allows knowledge distillation from large denoising networks in the form of a perceptual content loss. (3) Empirical analysis of our efficient model trained to specialize on different noise subranges. This opens additional avenue for model size reduction by sacrificing memory for compute. Extensive experimental validation shows that our efficient model produces high quality denoising results that compete with state-of-the-art large networks, while using significantly fewer parameters and MACs. On the Darmstadt Noise Dataset benchmark, we achieve a PSNR of 48.28dB, while using 263 times fewer MACs, and 17.6 times fewer parameters than the state-of-the-art network, which achieves 49.12dB.