# Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss

arXiv: https://arxiv.org/abs/1911.09428 · HTML: https://mlsanity.com/paper/1911.09428/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 13 of 13)

- [Self-Evolving Multi-Agent Systems via Textual Backpropagation](https://mlsanity.com/paper/2506.09046/) (2025)
- [CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference](https://mlsanity.com/paper/2501.15852/) (2025)
- [Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration](https://mlsanity.com/paper/2304.06976/) (2023)
- [Ultra-Range Gesture Recognition using a Web-Camera in Human-Robot Interaction](https://mlsanity.com/paper/2311.15361/) (2023)
- [Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation](https://mlsanity.com/paper/2509.05746/) (2025)
- [Space-Variant Total Variation boosted by learning techniques in few-view tomographic imaging](https://mlsanity.com/paper/2404.16900/) (2024)
- [Single-image reflection removal via self-supervised diffusion models](https://mlsanity.com/paper/2412.20466/) (2024)
- [FREDSR: Fourier Residual Efficient Diffusive GAN for Single Image Super Resolution](https://mlsanity.com/paper/2211.16678/) (2022)
- [City Scene Super-Resolution via Geometric Error Minimization](https://mlsanity.com/paper/2401.07272/) (2024)
- [Semi-supervised Chinese Poem-to-Painting Generation via Cycle-consistent Adversarial Networks](https://mlsanity.com/paper/2410.19307/) (2024)
- [CLIP-aware Domain-Adaptive Super-Resolution](https://mlsanity.com/paper/2505.12391/) (2025)
- [GEWDiff: Geometric Enhanced Wavelet-based Diffusion Model for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2511.07103/) (2025)
- [CLADE: Cycle Loss Augmented Degradation Enhancement for Unpaired Super-Resolution of Anisotropic Medical Images](https://mlsanity.com/paper/2303.11831/) (2023)

## Abstract (arXiv)

Single image super-resolution (SISR) is the task of inferring a high-resolution image from a single low-resolution image. Recent research on super-resolution has achieved great progress due to the development of deep convolutional neural networks in the field of computer vision. Existing super-resolution reconstruction methods have high performances in the criterion of Mean Square Error (MSE) but most methods fail to reconstruct an image with shape edges. To solve this problem, the mixed gradient error, which is composed by MSE and a weighted mean gradient error, is proposed in this work and applied to a modified U-net network as the loss function. The modified U-net removes all batch normalization layers and one of the convolution layers in each block. The operation reduces the number of parameters, and therefore accelerates the reconstruction. Compared with the existing image super-resolution algorithms, the proposed reconstruction method has better performance and time consumption. The experiments demonstrate that modified U-net network architecture with mixed gradient loss yields high-level results on three image datasets: SET14, BSD300, ICDAR2003. Code is available online.