mlsanityData to 7 Oct 2026

A Sub-band Approach to Deep Denoising Wavelet Networks and a Frequency-adaptive Loss for Perceptual Quality

arXiv 2102.07973 ↗First posted 16 Feb 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose two contributions to neural network based denoising. First, we propose applying separate convolutional layers to each sub-band of discrete wavelet transform (DWT) as opposed to the common usage of DWT which concatenates all sub-bands and applies a single convolution layer. We show that our approach to using DWT in neural networks improves the accuracy notably, due to keeping the sub-band order uncorrupted prior to inverse DWT. Our second contribution is a denoising loss based on top k-percent of errors in frequency domain. A neural network trained with this loss, adaptively focuses on frequencies that it fails to recover the most in each iteration. We show that this loss results into better perceptual quality by providing an image that is more balanced in terms of the errors in frequency components.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 31 references that are in the map. First posted on arXiv 16 Feb 2021.

Builds on

14 of 31 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  6. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  7. 2017The Perception-Distortion Tradeoffcited by 582
  8. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  9. 2018Residual Dense Network for Image Restorationcited by 181
  10. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  11. 2019GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modelingcited by 33
  12. 2019Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentationcited by 30
2 more
  1. 2020Frequency Domain-based Perceptual Loss for Super Resolutioncited by 7
  2. 2020Superkernel Neural Architecture Search for Image Denoisingcited by 4

Built on by

Not cited yet.