# FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform arXiv: https://arxiv.org/abs/2111.10800 ยท HTML: https://mlsanity.com/paper/2111.10800/ ## Key facts - Cited by 11 papers in the map (data through 14 Oct 2026). - Builds on 29 of its 43 references that are in the map. - First posted on arXiv 21 Nov 2021. ## Builds on (most cited first, 29 of 29) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016) - [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017) - [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016) - [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016) - [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017) - [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018) - [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018) - [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014) - [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021) - [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015) - [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018) - [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018) - [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021) - [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016) - [Sketch-based Manga Retrieval using Manga109 Dataset](https://mlsanity.com/paper/1510.04389/) (2015) - [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015) - [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021) - [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017) - [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019) - [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020) - [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019) - [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017) - [Compressed Video Action Recognition](https://mlsanity.com/paper/1712.00636/) (2017) - [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021) - [Towards Image Understanding from Deep Compression without Decoding](https://mlsanity.com/paper/1803.06131/) (2018) - [Deep Residual Learning in the JPEG Transform Domain](https://mlsanity.com/paper/1812.11690/) (2018) - [LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction](https://mlsanity.com/paper/1807.09388/) (2018) ## Built on by (most cited first, 11 of 11) - [The DeepSpeak Dataset](https://mlsanity.com/paper/2408.05366/) (2024) - [Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution](https://mlsanity.com/paper/2407.16232/) (2024) - [VSRM: A Robust Mamba-Based Framework for Video Super-Resolution](https://mlsanity.com/paper/2506.22762/) (2025) - [VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2205.12602/) (2022) - [Exploring Effective Mask Sampling Modeling for Neural Image Compression](https://mlsanity.com/paper/2306.05704/) (2023) - [MGHF: Multi-Granular High-Frequency Perceptual Loss for Image Super-Resolution](https://mlsanity.com/paper/2411.13548/) (2024) - [FADPNet: Frequency-Aware Dual-Path Network for Face Super-Resolution](https://mlsanity.com/paper/2506.14121/) (2025) - [NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization](https://mlsanity.com/paper/2512.23374/) (2025) - [A Scale-Arbitrary Image Super-Resolution Network Using Frequency-domain Information](https://mlsanity.com/paper/2212.04314/) (2022) - [Learning Single-Image Super-Resolution in the JPEG Compressed Domain](https://mlsanity.com/paper/2512.04284/) (2025) - [Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Training](https://mlsanity.com/paper/2604.20291/) (2026) ## Abstract (arXiv) Single image super-resolution(SISR) is an ill-posed problem that aims to obtain high-resolution (HR) output from low-resolution (LR) input, during which extra high-frequency information is supposed to be added to improve the perceptual quality. Existing SISR works mainly operate in the spatial domain by minimizing the mean squared reconstruction error. Despite the high peak signal-to-noise ratios(PSNR) results, it is difficult to determine whether the model correctly adds desired high-frequency details. Some residual-based structures are proposed to guide the model to focus on high-frequency features implicitly. However, how to verify the fidelity of those artificial details remains a problem since the interpretation from spatial-domain metrics is limited. In this paper, we propose FreqNet, an intuitive pipeline from the frequency domain perspective, to solve this problem. Inspired by existing frequency-domain works, we convert images into discrete cosine transform (DCT) blocks, then reform them to obtain the DCT feature maps, which serve as the input and target of our model. A specialized pipeline is designed, and we further propose a frequency loss function to fit the nature of our frequency-domain task. Our SISR method in the frequency domain can learn the high-frequency information explicitly, provide fidelity and good perceptual quality for the SR images. We further observe that our model can be merged with other spatial super-resolution models to enhance the quality of their original SR output.