Feature-Align Network and Knowledge Distillation for Efficient Denoising

03/02/2021
by   Lucas D. Young, et al.
37

Deep learning-based RAW image denoising is a quintessential problem in image restoration. Recent works have pushed the state-of-the-art in denoising image quality. However, many of these networks are computationally too expensive for efficient use in mobile devices. Here, we propose a novel network for efficient RAW denoising on mobile devices. Our contributions are: (1) An efficient encoder-decoder network augmented with a new Feature-Align layer to attend to spatially varying noise. (2) A new perceptual Feature Loss calculated in the RAW domain to preserve high frequency image content. (3) An analysis of the use of multiple models tuned to different subranges of noise levels. (4) An open-source RAW noisy-clean paired dataset with noise modeling, to facilitate research in RAW denoising. We evaluate the effectiveness of our proposed network and training techniques and show results that compete with the state-of-the-art network, while using significantly fewer parameters and MACs. On the Darmstadt Noise Dataset benchmark, we achieve a PSNR of 48.28dB, with 263 times fewer MACs, and 17.6 times fewer parameters than the state-of-the-art network, which achieves 49.12 dB.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 7

page 8

research
10/14/2020

Practical Deep Raw Image Denoising on Mobile Devices

Deep learning-based image denoising approaches have been extensively stu...
research
08/31/2020

Unpaired Learning of Deep Image Denoising

We investigate the task of learning blind image denoising networks from ...
research
04/29/2022

Multiple Degradation and Reconstruction Network for Single Image Denoising via Knowledge Distillation

Single image denoising (SID) has achieved significant breakthroughs with...
research
01/06/2017

Deep Class Aware Denoising

The increasing demand for high image quality in mobile devices brings fo...
research
03/20/2023

Zero-Shot Noise2Noise: Efficient Image Denoising without any Data

Recently, self-supervised neural networks have shown excellent image den...
research
03/31/2020

Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes

In recent years, the supervised learning strategy for real noisy image d...
research
05/17/2021

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report

Image denoising is one of the most critical problems in mobile photo pro...

Please sign up or login with your details

Forgot password? Click here to reset