Densely Residual Laplacian Super-Resolution

By Saeed Anwar, Nick Barnes. 2019

281 citations recorded by the source corpus.

Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images. However, existing algorithms often require very deep architectures and long training times. Furthermore, current convolutional neural networks for super-resolution are unable to exploit features at multiple scales and weigh them equally or at only static scale only, limiting their learning capability. In this exposition, we present a compact and accurate super-resolution algorithm, namely, densely residual laplacian network (DRLN). The proposed network employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. In addition, deep supervision is achieved via the densely concatenated residual blocks settings, which also helps in learning from high-level complex features. Moreover, we propose Laplacian attention to model the crucial features to learn the inter and intra-level dependencies between the feature maps. Furthermore, comprehensive quantitative and qualitative evaluations on low-resolution, noisy low-resolution, and real historical image benchmark datasets illustrate that our DRLN algorithm performs favorably against the state-of-the-art methods visually and accurately.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Radu Timofte
4. Fahad Shahbaz Khan
5. Ling Shao
6. Salman Hameed Khan
7. Dacheng Tao
8. Chen Change Loy

In Media Technology

1. Radu Timofte
2. Ming-Hsuan Yang
3. Chao Dong
4. Salman Hameed Khan
5. Luc Van Gool
6. Wangmeng Zuo
7. Saeed Anwar
8. Nick Barnes

In Generative Models

1. Radu Timofte
2. Chao Dong
3. Saeed Anwar
4. Nick Barnes
5. Salman Hameed Khan
6. Wangmeng Zuo
7. Jinjin Gu
8. Errui Ding

Citations in the corpus

• A Deep Journey into Super-resolution (2019, methodology): “More recently, densely residual Laplacian attention Network (DRLN) [74] is introduced to super-resolve the images.”
• Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, background): “In recent years, data-driven CNN architectures [7, 18, 92, 93, 105, 107] have been shown to outperform conventional restoration approaches [26,36,53,75].”
• Interpreting Super-Resolution Networks with Local Attribution Maps (2020, background): “, EDSR [32], RRDBNet [56], RCAN [59] and DRLN [7], have deeper architectures and bigger receptive fields.”
• Scaling up GANs for Text-to-Image Synthesis (2023, unknown): “Unlike traditional super-resolution techniques [2, 18, 47, 95] that aim to faithfully reproduce low-resolution inputs or handle image degradation like compression artifacts, our upsamplers for large-scale models serve a different purpose.”
• HINet: Half Instance Normalization Network for Image Restoration (2021, methodology): “The single-stage methods are widely used in image restoration tasks, and these methods generally improve the network capacity through the complex network structure [3, 60].”
• AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results (2020, methodology): “As shown in Fig[1], the multi-scale mechanism was integrated into the base block of RCAN in order to enlarge the receptive field.”
• Multi-Stage Progressive Image Restoration (2021, background): “Other single-stage approaches [5, 89, 97] incorporate dense connections [34].”