# Hierarchical Back Projection Network for Image Super-Resolution

arXiv: https://arxiv.org/abs/1906.06874 · HTML: https://mlsanity.com/paper/1906.06874/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [Variational AutoEncoder for Reference based Image Super-Resolution](https://mlsanity.com/paper/2106.04090/) (2021)
- [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://mlsanity.com/paper/2303.04336/) (2023)
- [SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices](https://mlsanity.com/paper/2101.07996/) (2021)
- [Feedback Pyramid Attention Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2106.06966/) (2021)
- [Laplacian Pyramid-like Autoencoder](https://mlsanity.com/paper/2208.12484/) (2022)
- [Efficient neural supersampling on a novel gaming dataset](https://mlsanity.com/paper/2308.01483/) (2023)
- [Fast Monte Carlo Rendering via Multi-Resolution Sampling](https://mlsanity.com/paper/2106.12802/) (2021)
- [Controllable Confidence-Based Image Denoising](https://mlsanity.com/paper/2106.09311/) (2021)
- [Auxiliary Features-Guided Super Resolution for Monte Carlo Rendering](https://mlsanity.com/paper/2310.13235/) (2023)
- [Domain Transfer in Latent Space (DTLS) Wins on Image Super-Resolution -- a Non-Denoising Model](https://mlsanity.com/paper/2311.02358/) (2023)
- [Local-Global Context-Aware and Structure-Preserving Image Super-Resolution](https://mlsanity.com/paper/2510.13649/) (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)

Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction. We adopt the back projection blocks in our proposed network to provide the error correlated up and down-sampling process to replace simple deconvolution and pooling process for better estimation. A new Softmax based Weighted Reconstruction (WR) process is used to combine the outputs of HG modules to further improve super-resolution. Experimental results on various datasets (including the validation dataset, NTIRE2019, of the Real Image Super-resolution Challenge) show that our proposed approach can achieve and improve the performance of the state-of-the-art methods for different scaling factors.