# Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions

arXiv: https://arxiv.org/abs/2605.24621 · HTML: https://mlsanity.com/paper/2605.24621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 7 of 7)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring](https://mlsanity.com/paper/2110.05803/) (2021)
- [Complex-valued neural networks for machine learning on non-stationary physical data](https://mlsanity.com/paper/1905.12321/) (2019)
- [Neural network is heterogeneous: Phase matters more](https://mlsanity.com/paper/2111.02014/) (2021)

## Abstract (arXiv)

Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in global averaging. We propose Phase-Aware Scattering Encoder-Decoder, which restores this information by explicitly preserving phase in skip connections. On image denoising (BSD68), breaking translation invariance improves PSNR by +2.17~dB; phase preservation adds +1.03~dB. A novel spatial shuffling ablation (-1.26~dB penalty) demonstrates phase encodes location-dependent structure. We conduct a preliminary extensibility study on a second dense prediction task (ISIC skin lesion segmentation), with full cross-validation as ongoing work. This work advances principled wavelet-deep learning integration, showing how phase information complements scattering's stability-expressiveness trade-off in pixel-level prediction.