# Laplacian Pyramid-like Autoencoder

arXiv: https://arxiv.org/abs/2208.12484 · HTML: https://mlsanity.com/paper/2208.12484/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 25 of 25)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Multi-level Wavelet-CNN for Image Restoration](https://mlsanity.com/paper/1805.07071/) (2018)
- [DeepRED: Deep Image Prior Powered by RED](https://mlsanity.com/paper/1903.10176/) (2019)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search](https://mlsanity.com/paper/1901.07261/) (2019)
- [High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network](https://mlsanity.com/paper/2105.09188/) (2021)
- [Densely Residual Laplacian Super-Resolution](https://mlsanity.com/paper/1906.12021/) (2019)
- [Learned Image Downscaling for Upscaling using Content Adaptive Resampler](https://mlsanity.com/paper/1907.12904/) (2019)
- [AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning](https://mlsanity.com/paper/2102.01386/) (2021)
- [Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer](https://mlsanity.com/paper/2104.05376/) (2021)
- [Variational AutoEncoder for Reference based Image Super-Resolution](https://mlsanity.com/paper/2106.04090/) (2021)
- [Image Super-Resolution via Attention based Back Projection Networks](https://mlsanity.com/paper/1910.04476/) (2019)
- [TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inference](https://mlsanity.com/paper/2009.00748/) (2020)
- [AutoAssist: A Framework to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1905.03381/) (2019)
- [Hierarchical Back Projection Network for Image Super-Resolution](https://mlsanity.com/paper/1906.06874/) (2019)
- [Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networks](https://mlsanity.com/paper/1712.07493/) (2017)
- [Lightweight Feature Fusion Network for Single Image Super-Resolution](https://mlsanity.com/paper/1902.05694/) (2019)

## Built on by (most cited first, 2 of 2)

- [Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps](https://mlsanity.com/paper/2501.06999/) (2025)
- [Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Process](https://mlsanity.com/paper/2601.09410/) (2026)

## Abstract (arXiv)

In this paper, we develop the Laplacian pyramid-like autoencoder (LPAE) by adding the Laplacian pyramid (LP) concept widely used to analyze images in Signal Processing. LPAE decomposes an image into the approximation image and the detail image in the encoder part and then tries to reconstruct the original image in the decoder part using the two components. We use LPAE for experiments on classifications and super-resolution areas. Using the detail image and the smaller-sized approximation image as inputs of a classification network, our LPAE makes the model lighter. Moreover, we show that the performance of the connected classification networks has remained substantially high. In a super-resolution area, we show that the decoder part gets a high-quality reconstruction image by setting to resemble the structure of LP. Consequently, LPAE improves the original results by combining the decoder part of the autoencoder and the super-resolution network.