paper-with-me

홈 › Papers

A Cosine Network for Image Super-Resolution

2026-01-23 · Chunwei Tian, Chengyuan Zhang, Bob Zhang, Zhiwu Li, C. L. Philip Chen, David Zhang arxiv

Deep convolutional neural networks can use hierarchical information to progressively extract structural information to recover high-quality images. However, preserving the effectiveness of the obtained structural information is important in image super-resolution. In this paper, we propose a cosine network for image super-resolution (CSRNet) by improving a network architecture and optimizing the training strategy. To extract complementary homologous structural information, odd and even heterogeneous blocks are designed to enlarge the architectural differences and improve the performance of image super-resolution. Combining linear and non-linear structural information can overcome the drawback of homologous information and enhance the robustness of the obtained structural information in image super-resolution. Taking into account the local minimum of gradient descent, a cosine annealing mechanism is used to optimize the training procedure by performing warm restarts and adjusting the learning rate. Experimental results illustrate that the proposed CSRNet is competitive with state-of-the-art methods in image super-resolution.

📄 PDF Abstract BibTeX arXiv:2601.16413

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-Resolution

Similar Papers 제목 키워드 기반

Discrete Cosine Transform Network for Guided Depth Map Super-Resolution

2021-04-14 · CVPR 2022 1 · Zixiang Zhao, Jiangshe Zhang, Shuang Xu, Zudi Lin 외

Guided depth super-resolution (GDSR) is an essential topic in multi-modal image processing, which reconstructs high-resolution (HR) depth maps from low-resolution ones collected with suboptimal conditions with the help o…

Depth EstimationDepth Map Super-ResolutionSuper-Resolution

A Tree-guided CNN for image super-resolution

2025-06-03 · Chunwei Tian, Mingjian Song, Xiaopeng Fan, Xiangtao Zheng 외

Deep convolutional neural networks can extract more accurate structural information via deep architectures to obtain good performance in image super-resolution. However, it is not easy to find effect of important layers …

Image Super-ResolutionSuper-Resolution

FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform

2021-11-21 · Runyuan Cai, Yue Ding, Hongtao Lu

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…

Image Super-ResolutionSuper-Resolution

Generative adversarial network-based image super-resolution using perceptual content losses

2018-09-13 · Manri Cheon, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee

In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion. Based on good performance of a recently developed model for super-resoluti…

Generative Adversarial NetworkImage Super-ResolutionSuper-Resolution

Learning Single-Image Super-Resolution in the JPEG Compressed Domain

2025-12-03 · Sruthi Srinivasan, Elham Shakibapour, Rajy Rawther, Mehdi Saeedi arxiv

Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that li…

Image Super-Resolution