Global Learnable Attention for Single Image Super-Resolution
- URL: http://arxiv.org/abs/2212.01057v1
- Date: Fri, 2 Dec 2022 09:47:21 GMT
- Title: Global Learnable Attention for Single Image Super-Resolution
- Authors: Jian-Nan Su, Min Gan, Guang-Yong Chen, Jia-Li Yin, and C. L. Philip
Chen
- Abstract summary: We propose a Global Learnable Attention (GLA) to adaptively modify similarity scores of non-local textures during training.
The GLA can explore non-local textures with low-similarity but more accurate details to repair severely damaged textures.
Based on the GLA, we constructed a Deep Learnable Similarity Network (DLSN) which achieves state-of-the-art performance for SISR tasks.
- Score: 68.2129989450593
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Self-similarity is valuable to the exploration of non-local textures in
single image super-resolution (SISR). Researchers usually assume that the
importance of non-local textures is positively related to their similarity
scores. In this paper, we surprisingly found that when repairing severely
damaged query textures, some non-local textures with low-similarity which are
closer to the target can provide more accurate and richer details than the
high-similarity ones. In these cases, low-similarity does not mean inferior but
is usually caused by different scales or orientations. Utilizing this finding,
we proposed a Global Learnable Attention (GLA) to adaptively modify similarity
scores of non-local textures during training instead of only using a fixed
similarity scoring function such as the dot product. The proposed GLA can
explore non-local textures with low-similarity but more accurate details to
repair severely damaged textures. Furthermore, we propose to adopt Super-Bit
Locality-Sensitive Hashing (SB-LSH) as a preprocessing method for our GLA. With
the SB-LSH, the computational complexity of our GLA is reduced from quadratic
to asymptotic linear with respect to the image size. In addition, the proposed
GLA can be integrated into existing deep SISR models as an efficient general
building block. Based on the GLA, we constructed a Deep Learnable Similarity
Network (DLSN), which achieves state-of-the-art performance for SISR tasks of
different degradation types (e.g. blur and noise). Our code and a pre-trained
DLSN have been uploaded to GitHub{\dag} for validation.
Related papers
- AbsGS: Recovering Fine Details for 3D Gaussian Splatting [10.458776364195796]
3D Gaussian Splatting (3D-GS) technique couples 3D primitives with differentiable Gaussianization to achieve high-quality novel view results.
However, 3D-GS frequently suffers from over-reconstruction issue in intricate scenes containing high-frequency details, leading to blurry rendered images.
We present a comprehensive analysis of the cause of aforementioned artifacts, namely gradient collision.
Our strategy efficiently identifies large Gaussians in over-reconstructed regions, and recovers fine details by splitting.
arXiv Detail & Related papers (2024-04-16T11:44:12Z) - Combining Attention Module and Pixel Shuffle for License Plate
Super-Resolution [3.8831062015253055]
This work focuses on license plate (LP) reconstruction in low-resolution and low-quality images.
We present a Single-Image Super-Resolution (SISR) approach that extends the attention/transformer module concept.
In our experiments, the proposed method outperformed the baselines both quantitatively and qualitatively.
arXiv Detail & Related papers (2022-10-30T13:05:07Z) - Boosting Few-shot Fine-grained Recognition with Background Suppression
and Foreground Alignment [53.401889855278704]
Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples.
We propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local to local (L2L) similarity metric.
Experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state-of-the-art by a large margin.
arXiv Detail & Related papers (2022-10-04T07:54:40Z) - Global and Local Texture Randomization for Synthetic-to-Real Semantic
Segmentation [40.556020857447535]
We propose two simple yet effective texture randomization mechanisms, Global Randomization (GTR) and Local Texture Randomization (LTR)
GTR is proposed to randomize the texture of source images into diverse texture styles.
LTR is proposed to generate diverse local regions for partially stylizing the source images.
arXiv Detail & Related papers (2021-08-05T05:14:49Z) - Discriminator-Free Generative Adversarial Attack [87.71852388383242]
Agenerative-based adversarial attacks can get rid of this limitation.
ASymmetric Saliency-based Auto-Encoder (SSAE) generates the perturbations.
The adversarial examples generated by SSAE not only make thewidely-used models collapse, but also achieves good visual quality.
arXiv Detail & Related papers (2021-07-20T01:55:21Z) - A Spectral-Spatial-Dependent Global Learning Framework for Insufficient
and Imbalanced Hyperspectral Image Classification [16.93904035334754]
spectral-spatial dependent global learning (SSDGL) framework based on global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM)
SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods.
arXiv Detail & Related papers (2021-05-29T15:39:03Z) - Making Affine Correspondences Work in Camera Geometry Computation [62.7633180470428]
Local features provide region-to-region rather than point-to-point correspondences.
We propose guidelines for effective use of region-to-region matches in the course of a full model estimation pipeline.
Experiments show that affine solvers can achieve accuracy comparable to point-based solvers at faster run-times.
arXiv Detail & Related papers (2020-07-20T12:07:48Z) - Cross-Scale Internal Graph Neural Network for Image Super-Resolution [147.77050877373674]
Non-local self-similarity in natural images has been well studied as an effective prior in image restoration.
For single image super-resolution (SISR), most existing deep non-local methods only exploit similar patches within the same scale of the low-resolution (LR) input image.
This is achieved using a novel cross-scale internal graph neural network (IGNN)
arXiv Detail & Related papers (2020-06-30T10:48:40Z) - Image Fine-grained Inpainting [89.17316318927621]
We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields.
To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss.
We also employ a discriminator with local and global branches to ensure local-global contents consistency.
arXiv Detail & Related papers (2020-02-07T03:45:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.