ARM: Any-Time Super-Resolution Method

• URL: http://arxiv.org/abs/2203.10812v1
• Date: Mon, 21 Mar 2022 09:06:26 GMT
• Title: ARM: Any-Time Super-Resolution Method
• Authors: Bohong Chen, Mingbao Lin, Kekai Sheng, Mengdan Zhang, Peixian Chen, Ke Li, Liujuan Cao, Rongrong Ji
• Abstract summary: An Any-time super-Resolution Method (ARM) is proposed to tackle the over- parameterized single image super-resolution (SISR) models. Our ARM is motivated by three observations: (1) The performance of different image patches varies with SISR networks of different sizes; (2) There is a tradeoff between computation overhead and performance of the reconstructed image; and (3) Given an input image, its edge information can be an effective option to estimate its PSNR.
• Score: 72.98897502507789
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes an Any-time super-Resolution Method (ARM) to tackle the over-parameterized single image super-resolution (SISR) models. Our ARM is motivated by three observations: (1) The performance of different image patches varies with SISR networks of different sizes. (2) There is a tradeoff between computation overhead and performance of the reconstructed image. (3) Given an input image, its edge information can be an effective option to estimate its PSNR. Subsequently, we train an ARM supernet containing SISR subnets of different sizes to deal with image patches of various complexity. To that effect, we construct an Edge-to-PSNR lookup table that maps the edge score of an image patch to the PSNR performance for each subnet, together with a set of computation costs for the subnets. In the inference, the image patches are individually distributed to different subnets for a better computation-performance tradeoff. Moreover, each SISR subnet shares weights of the ARM supernet, thus no extra parameters are introduced. The setting of multiple subnets can well adapt the computational cost of SISR model to the dynamically available hardware resources, allowing the SISR task to be in service at any time. Extensive experiments on resolution datasets of different sizes with popular SISR networks as backbones verify the effectiveness and the versatility of our ARM. The source code is available at \url{https://github.com/chenbong/ARM-Net}.

Related papers

• Jointly RS Image Deblurring and Super-Resolution with Adjustable-Kernel and Multi-Domain Attention [43.3544131406078]
  Real-world RS images often suffer from a complex combination of global low-resolution degeneration and local degeneration. We propose a dual-branch parallel network named AKMDNet for the JRSIDSR task. AKMDNet consists of two main branches: deblurring and super-resolution branches.
  arXiv  Detail & Related papers  (2024-12-07T16:44:31Z)
• ASANet: Asymmetric Semantic Aligning Network for RGB and SAR image land cover classification [5.863175733097434]
  We propose a novel architecture, named the Asymmetric Semantic Aligning Network (ASANet) to address the issue of asymmetry at the feature level. The proposed ASANet effectively learns feature correlations between the two modalities and eliminates noise caused by feature differences. We have established a new RGB-SAR multimodal dataset, on which our ASANet outperforms other mainstream methods with improvements ranging from 1.21% to 17.69%.
  arXiv  Detail & Related papers  (2024-12-03T00:03:33Z)
• DVMSR: Distillated Vision Mamba for Efficient Super-Resolution [7.551130027327461]
  We propose DVMSR, a novel lightweight Image SR network that incorporates Vision Mamba and a distillation strategy. Our proposed DVMSR can outperform state-of-the-art efficient SR methods in terms of model parameters.
  arXiv  Detail & Related papers  (2024-05-05T17:34:38Z)
• Binarized Spectral Compressive Imaging [59.18636040850608]
  Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources. We propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet) BiSRNet is derived by using the proposed techniques to binarize the base model.
  arXiv  Detail & Related papers  (2023-05-17T15:36:08Z)
• LR-CSNet: Low-Rank Deep Unfolding Network for Image Compressive Sensing [19.74767410530179]
  Deep unfolding networks (DUNs) have proven to be a viable approach to compressive sensing (CS) In this work, we propose a DUN called low-rank CS network (LR-CSNet) for natural image CS. Our experiments on three widely considered datasets demonstrate the promising performance of LR-CSNet.
  arXiv  Detail & Related papers  (2022-12-18T13:54:11Z)
• Lightweight Image Super-Resolution with Hierarchical and Differentiable Neural Architecture Search [38.83764580480486]
  Single Image Super-Resolution (SISR) tasks have achieved significant performance with deep neural networks. We propose a novel differentiable Neural Architecture Search (NAS) approach on both the cell-level and network-level to search for lightweight SISR models.
  arXiv  Detail & Related papers  (2021-05-09T13:30:16Z)
• Super-resolving Compressed Images via Parallel and Series Integration of Artifact Reduction and Resolution Enhancement [24.45801094210365]
  We propose a novel compressed image super resolution (CISR) framework based on parallel and series integration of artifact removal and resolution enhancement. A unique property of our CSIR system is that a single trained model is able to super-resolve LR images compressed by different methods to various qualities.
  arXiv  Detail & Related papers  (2021-03-02T13:04:28Z)
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network [63.69237156340457]
  We present and advocate an explainable approach toward SISR named model-guided deep unfolding network (MoG-DUN) MoG-DUN is accurate (producing fewer aliasing artifacts), computationally efficient (with reduced model parameters), and versatile (capable of handling multiple degradations) The superiority of the proposed MoG-DUN method to existing state-of-theart image methods including RCAN, SRDNF, and SRFBN is substantiated by extensive experiments on several popular datasets and various degradation scenarios.
  arXiv  Detail & Related papers  (2020-09-14T08:23:37Z)
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS [63.48801313087118]
  We propose a new method for image superresolution using deep residual network with dense skip connections. The proposed method won the first place in all three tracks of the AIM 2020 Real Image Super-Resolution Challenge.
  arXiv  Detail & Related papers  (2020-09-02T22:33:23Z)
• MDCN: Multi-scale Dense Cross Network for Image Super-Resolution [35.59973281360541]
  We propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB)
  arXiv  Detail & Related papers  (2020-08-30T03:50:19Z)
• Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution [83.70890515772456]
  We build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR. We consider the inter-scale correlations of features, and devise a sequential multi-scale block (SMB) to progressively explore the hierarchical information. Experiment results show SHSR achieves superior quantitative performance and visual quality to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-19T01:35:53Z)
• Lightweight image super-resolution with enhanced CNN [82.36883027158308]
  Deep convolutional neural networks (CNNs) with strong expressive ability have achieved impressive performances on single image super-resolution (SISR) We propose a lightweight enhanced SR CNN (LESRCNN) with three successive sub-blocks, an information extraction and enhancement block (IEEB), a reconstruction block (RB) and an information refinement block (IRB) IEEB extracts hierarchical low-resolution (LR) features and aggregates the obtained features step-by-step to increase the memory ability of the shallow layers on deep layers for SISR. RB converts low-frequency features into high-frequency features by fusing global
  arXiv  Detail & Related papers  (2020-07-08T18:03:40Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)

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.