# Deep Back-Projection Networks for Single Image Super-resolution

arXiv: https://arxiv.org/abs/1904.05677 · HTML: https://mlsanity.com/paper/1904.05677/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

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

- [Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation](https://mlsanity.com/paper/2211.13676/) (2022)
- [Human Guided Ground-truth Generation for Realistic Image Super-resolution](https://mlsanity.com/paper/2303.13069/) (2023)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning](https://mlsanity.com/paper/2205.05264/) (2022)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [Toward Real-World Light Field Super-Resolution](https://mlsanity.com/paper/2305.18994/) (2023)
- [Burst Super-Resolution with Diffusion Models for Improving Perceptual Quality](https://mlsanity.com/paper/2403.19428/) (2024)
- [EarthGen: Generating the World from Top-Down Views](https://mlsanity.com/paper/2409.01491/) (2024)
- [Efficient Burst Super-Resolution with One-step Diffusion](https://mlsanity.com/paper/2507.13607/) (2025)
- [Working memory inspired hierarchical video decomposition with transformative representations](https://mlsanity.com/paper/2204.10105/) (2022)
- [Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures](https://mlsanity.com/paper/2404.06294/) (2024)
- [Improving Multi-View Stereo via Super-Resolution](https://mlsanity.com/paper/2107.13261/) (2021)
- [Depth Estimation fusing Image and Radar Measurements with Uncertain Directions](https://mlsanity.com/paper/2403.15787/) (2024)
- [A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Method](https://mlsanity.com/paper/2412.09846/) (2024)
- [Efficient Cost-and-Quality Controllable Arbitrary-scale Super-resolution with Fourier Constraints](https://mlsanity.com/paper/2510.23978/) (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)

Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), the winner of two image super-resolution challenges (NTIRE2018 and PIRM2018), that exploit iterative up- and down-sampling layers. These layers are formed as a unit providing an error feedback mechanism for projection errors. We construct mutually-connected up- and down-sampling units each of which represents different types of low- and high-resolution components. We also show that extending this idea to demonstrate a new insight towards more efficient network design substantially, such as parameter sharing on the projection module and transition layer on projection step. The experimental results yield superior results and in particular establishing new state-of-the-art results across multiple data sets, especially for large scaling factors such as 8x.