EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration

Xu, Ruikang; Xiao, Zeyu; Huang, Jie; Zhang, Yueyi; Xiong, Zhiwei

doi:10.1109/cvprw53098.2021.00052

Cited by 29 publications

(13 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lim et al [12] adopt a wider model structure to increase model parameters to achieve a better performance. The EDPN [26] replicates the input image into a sequence and employs deformable convolutions to learn image internal self-similarity. Liu et al [27] introduced window transformers [28] into the SR domain, which can strengthen the correlation of image globalization information.…”

Section: A Deep Network For Srmentioning

confidence: 99%

See 1 more Smart Citation

DARN: Distance Attention Residual Network for Lightweight Remote-Sensing Image Superresolution

Wang

Chen

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The application of single-image superresolution (SISR) in remote sensing is of great significance. Although the state-of-the-art convolution neural network (CNN)-based SISR methods have achieved excellent results, the large model and slow speed make it difficult to deploy in real remote sensing tasks. In this article, we propose a compact and efficient distance attention residual network (DARN) to achieve a better compromise between model accuracy and complexity. The distance attention residual connection block (DARCB), the core component of the DARN, uses multistage feature aggregation to learn more accurate feature representations. The main branch of the DARCB adopts a shallow residual block (SRB) to flexibly learn residual information to ensure the robustness of the model. We also propose a distance attention block (DAB) as a bridge between the main branch and the branch of the DARCB; the DAB can effectively alleviate the loss of detail features in the deep CNN extraction process. Experimental results on two remote sensing and five super-resolution benchmark datasets demonstrate that the DARN achieves a better compromise than existing methods in terms of performance and model complexity. In addition, the DARN achieves the optimal solution compared with the state-of-the-art lightweight remote sensing SISR method in terms of parameter amount, computation amount, and inference speed. Our code will be available at https://github.com/candygogogogo/DARN.

show abstract

Section: A Deep Network For Srmentioning

confidence: 99%

“…where f represents connecting multistage features in the spatial dimension. Based on the relevant work [13], [23], [24], [26], [27] experience of other researchers, the DARN is optimized using the L 1 generalized loss function. It can be expressed as…”

Section: A Framework Viewmentioning

confidence: 99%

DARN: Distance Attention Residual Network for Lightweight Remote-Sensing Image Superresolution

Wang

Chen

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The straightforward way for multi-scale architecture is to separately feed multi-/single-resolution images/features into single/multiple subnetworks, and then fuse the outputs as a result [44,19,46,20,23]. For example, HRNet [36] proposed a multi-scale network by gradually adding high-to-low resolution subnetworks and repeating multi-scale fusions for human pose estimation.…”

Section: Multi-scale Architecturesmentioning

confidence: 99%

Multi-Scale Adaptive Network for Single Image Denoising

Gou¹,

Hu²,

Lv³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-scale architectures have shown effectiveness in a variety of tasks including single image denoising, thanks to appealing cross-scale complementarity. However, existing methods treat different scale features equally without considering their scale-specific characteristics, i.e., the within-scale characteristics are ignored. In this paper, we reveal this missing piece for multi-scale architecture design and accordingly propose a novel Multi-Scale Adaptive Network (MSANet) for single image denoising. To be specific, MSANet simultaneously embraces the withinscale characteristics and the cross-scale complementarity thanks to three novel neural blocks, i.e., adaptive feature block (AFeB), adaptive multi-scale block (AMB), and adaptive fusion block (AFuB). In brief, AFeB is designed to adaptively select details and filter noises, which is highly expected for fine-grained features. AMB could enlarge the receptive field and aggregate the multi-scale information, which is designed to satisfy the demands of both fine-and coarse-grained features. AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which is used to fuse the features with varying characteristics from coarse to fine. Extensive experiments on both three real and six synthetic noisy image datasets show the superiority of MSANet compared with 12 methods.

show abstract

“…These approaches often utilize networks with encoder-decoder structure [40] combined with efficient blocks for complex spatial distribution of aberrations [19], [20], [22], [23], [41], obtaining more efficient and robust results than traditional methods. Other networks for image restoration with spatially diverse degradation are also fit for aberration correction which fuse multi-scale information [38], [42], and use deformable convolution [43], [44] or dynamic convolution [45]. Nevertheless, these methods are usually evaluated only on datasets and rarely applied to image restoration of real lenses.…”

Section: Related Work a Aberration Correction Through Computationmentioning

confidence: 99%

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Jiang¹,

Sheng²,

Sun³

et al. 2022

Preprint

View full text Add to dashboard Cite

Panoramic Annular Lens (PAL), composed of few lenses, has great potential in panoramic surrounding sensing tasks for mobile and wearable devices because of its tiny size and large Field of View (FoV). However, the image quality of tiny-volume PAL confines to optical limit due to the lack of lenses for aberration correction. In this paper, we propose an Annular Computational Imaging (ACI) framework to break the optical limit of light-weight PAL design. To facilitate learning-based image restoration, we introduce a wave-based simulation pipeline for panoramic imaging and tackle the synthetic-to-real gap through multiple data distributions. The proposed pipeline can be easily adapted to any PAL with design parameters and is suitable for loose-tolerance designs. Furthermore, we design the Physics Informed Image Restoration Network (PI 2 RNet), considering the physical priors of panoramic imaging and physics-informed learning. At the dataset level, we create the DIVPano dataset and the extensive experiments on it illustrate that our proposed network sets the new state of the art in the panoramic image restoration under spatially-variant degradation. In addition, the evaluation of the proposed ACI on a simple PAL with only 3 spherical lenses reveals the delicate balance between high-quality panoramic imaging and compact design. To the best of our knowledge, we are the first to explore Computational Imaging (CI) in PAL. Code and datasets will be made publicly available at https://github.com/zju-jiangqi/ACI-PI2RNet.

show abstract

EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration

Cited by 29 publications

References 50 publications

DARN: Distance Attention Residual Network for Lightweight Remote-Sensing Image Superresolution

DARN: Distance Attention Residual Network for Lightweight Remote-Sensing Image Superresolution

Multi-Scale Adaptive Network for Single Image Denoising

Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens

Contact Info

Product

Resources

About