mlsanityData to 14 Oct 2026

Laplacian Pyramid-like Autoencoder

arXiv 2208.12484 ↗First posted 26 Aug 2022cs.CV cs.LG eess.IVcited by 2

Not on the map. Why?

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.

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

25 of 45 references.

References · 25

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  3. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  4. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  5. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  6. 2016Tutorial on Variational Autoencoderscited by 409
  7. 2015Adversarial Autoencoderscited by 364
  8. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  9. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  10. 2018Multi-level Wavelet-CNN for Image Restorationcited by 184
  11. 2019DeepRED: Deep Image Prior Powered by REDcited by 85
  12. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
13 more
  1. 2019Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Searchcited by 66
  2. 2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
  3. 2019Densely Residual Laplacian Super-Resolutioncited by 57
  4. 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
  5. 2021AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuningcited by 48
  6. 2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
  7. 2021Variational AutoEncoder for Reference based Image Super-Resolutioncited by 18
  8. 2019Image Super-Resolution via Attention based Back Projection Networkscited by 16
  9. 2020TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inferencecited by 16
  10. 2019AutoAssist: A Framework to Accelerate Training of Deep Neural Networkscited by 14
  11. 2019Hierarchical Back Projection Network for Image Super-Resolutioncited by 12
  12. 2017Learning a Wavelet-like Auto-Encoder to Accelerate Deep Neural Networkscited by 8
  13. 2019Lightweight Feature Fusion Network for Single Image Super-Resolutioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Mapscited by 2
  2. 2026Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Processcited by 0