# Is the deconvolution layer the same as a convolutional layer?

arXiv: https://arxiv.org/abs/1609.07009 · HTML: https://mlsanity.com/paper/1609.07009/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2016.

## Built on by (most cited first, 16 of 16)

- [FeatUp: A Model-Agnostic Framework for Features at Any Resolution](https://mlsanity.com/paper/2403.10516/) (2024)
- [LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models](https://mlsanity.com/paper/2504.14032/) (2025)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution](https://mlsanity.com/paper/2209.10305/) (2022)
- [Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition](https://mlsanity.com/paper/2108.01569/) (2021)
- [OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression](https://mlsanity.com/paper/2107.09179/) (2021)
- [FeatSharp: Your Vision Model Features, Sharper](https://mlsanity.com/paper/2502.16025/) (2025)
- [An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling](https://mlsanity.com/paper/2107.07647/) (2021)
- [Quaternion Generative Adversarial Neural Networks and Applications to Color Image Inpainting](https://mlsanity.com/paper/2406.11567/) (2024)
- [Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation](https://mlsanity.com/paper/2505.02075/) (2025)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [A new smart-cropping pipeline for prostate segmentation using deep learning networks](https://mlsanity.com/paper/2107.02476/) (2021)
- [On the Robustness and Generalization of Deep Learning Driven Full Waveform Inversion](https://mlsanity.com/paper/2111.14220/) (2021)
- [More complex encoder is not all you need](https://mlsanity.com/paper/2309.11139/) (2023)
- [Addressing Diverging Training Costs using BEVRestore for High-resolution Bird's Eye View Map Construction](https://mlsanity.com/paper/2405.01016/) (2024)
- [Improving Generative Adversarial Networks for Video Super-Resolution](https://mlsanity.com/paper/2406.16359/) (2024)

## Abstract (arXiv)

In this note, we want to focus on aspects related to two questions most people asked us at CVPR about the network we presented. Firstly, What is the relationship between our proposed layer and the deconvolution layer? And secondly, why are convolutions in low-resolution (LR) space a better choice? These are key questions we tried to answer in the paper, but we were not able to go into as much depth and clarity as we would have liked in the space allowance. To better answer these questions in this note, we first discuss the relationships between the deconvolution layer in the forms of the transposed convolution layer, the sub-pixel convolutional layer and our efficient sub-pixel convolutional layer. We will refer to our efficient sub-pixel convolutional layer as a convolutional layer in LR space to distinguish it from the common sub-pixel convolutional layer. We will then show that for a fixed computational budget and complexity, a network with convolutions exclusively in LR space has more representation power at the same speed than a network that first upsamples the input in high resolution space.