paper-with-me

홈 › Papers

Super-Resolution Image Reconstruction Based on Self-Calibrated Convolutional GAN

2021-06-10 · Yibo Guo, Haidi Wang, Yiming Fan, Shunyao Li, Mingliang Xu

With the effective application of deep learning in computer vision, breakthroughs have been made in the research of super-resolution images reconstruction. However, many researches have pointed out that the insufficiency of the neural network extraction on image features may bring the deteriorating of newly reconstructed image. On the other hand, the generated pictures are sometimes too artificial because of over-smoothing. In order to solve the above problems, we propose a novel self-calibrated convolutional generative adversarial networks. The generator consists of feature extraction and image reconstruction. Feature extraction uses self-calibrated convolutions, which contains four portions, and each portion has specific functions. It can not only expand the range of receptive fields, but also obtain long-range spatial and inter-channel dependencies. Then image reconstruction is performed, and finally a super-resolution image is reconstructed. We have conducted thorough experiments on different datasets including set5, set14 and BSD100 under the SSIM evaluation method. The experimental results prove the effectiveness of the proposed network.

📄 PDF Abstract BibTeX arXiv:2106.05545

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionSSIMSuper-Resolution

Similar Papers 제목 키워드 기반

Self-Supervised Uncertainty Estimation For Super-Resolution of Satellite Images

2026-03-14 · Zhe Zheng, Valéry Dewil, Pablo Arias arxiv

Super-resolution (SR) of satellite imagery is challenging due to the lack of paired low-/high-resolution data. Recent self-supervised SR methods overcome this limitation by exploiting the temporal redundancy in burst obs…

Image Super-ResolutionImage Reconstruction

A self-adapting super-resolution structures framework for automatic design of GAN

2021-06-10 · Yibo Guo, Haidi Wang, Yiming Fan, Shunyao Li 외

With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the models have a greater impact on model per…

Bayesian OptimizationGenerative Adversarial NetworkImage ReconstructionSuper-Resolution

Self-Calibrated Efficient Transformer for Lightweight Super-Resolution

2022-04-19 · Wenbin Zou, Tian Ye, Weixin Zheng, Yunchen Zhang 외

Recently, deep learning has been successfully applied to the single-image super-resolution (SISR) with remarkable performance. However, most existing methods focus on building a more complex network with a large number o…

Image Super-ResolutionSuper-Resolution

HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

2026-06-28 · Yiming Jiang, Hanzhang Tu, Wenfeng Song, Siyou Lin 외 arxiv

Uncalibrated volumetric video streaming for human reconstruction is essential for holographic communication and AR/VR, yet remains challenging due to the need for temporal consistency and computational efficiency from sp…

Computational EfficiencyVideo Reconstruction

SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

2023-04-01 · CVPR 2023 1 · Yukang Cao, Kai Han, Kwan-Yee K. Wong

We address the problem of clothed human reconstruction from a single image or uncalibrated multi-view images. Existing methods struggle with reconstructing detailed geometry of a clothed human and often require a calibra…