☆ 4.6 Article

Domain-agnostic single-image super-resolution via a meta-transfer neural architecture search

NEUROCOMPUTING (2023)

Related references

Note: Only part of the references are listed.

Article Optics

Super-resolution reconstruction of infrared images based on a convolutional neural network with skip connections

Yan Zou et al.

Summary: This paper presents a super-resolution reconstruction method for infrared images based on a convolutional neural network with skip connections, which introduces global and local residual learning to reduce complexity and accelerate convergence. Multiple convolution and deconvolution layers are used for feature extraction and restoration, with the addition of skip connections and channel fusion to increase the number of feature maps and enhance image detail restoration. Compared to previous methods, this approach excels in acquiring high-resolution details in infrared images.

OPTICS AND LASERS IN ENGINEERING (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization

Haoyue Bai et al.

Summary: The paper introduces a robust neural architecture search method, NAS-OoD, which optimizes architecture based on performance on generated OoD data. Experimental results show superior performance on various OoD generalization benchmarks, with a reduction in error rate by over 70% compared to the state-of-the-art method on a real industry dataset.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Sparsity in Image Super-Resolution for Efficient Inference

Longguang Wang et al.

Summary: This study introduces a Sparse Mask SR network to improve inference efficiency of SR networks by learning sparse masks to prune redundant computation while maintaining comparable performance.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

MR Image Super-Resolution with Squeeze and Excitation Reasoning Attention Network

Yulun Zhang et al.

Summary: The paper proposes SERAN network for accurate MR image super-resolution, enhancing the network's focus on more informative regions and structures in the image with global descriptors, refining global descriptors further through adaptive attention vectors, and recalibrating feature responses for accurate details and texture reconstruction. This approach surpasses state-of-the-art methods on benchmarks quantitatively and visually.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Scene Text Telescope: Text-Focused Scene Image Super-Resolution

Jingye Chen et al.

Summary: The study introduces a text-focused super-resolution framework, which utilizes Transformer and self-attention module to extract sequential information, and position-aware and content-aware modules to emphasize character position and content. Weighted cross-entropy loss is used to address the issue of indistinguishable characters in low-resolution conditions.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment

Soo Ye Kim et al.

Summary: Our proposed blind SR framework based on kernel-oriented adaptive local adjustment (KOALA), called KOALAnet, outperforms recent blind SR methods and produces the most natural results for artistic photographs with intentional blur.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Flow-based Kernel Prior with Application to Blind Super-Resolution

Jingyun Liang et al.

Summary: This paper proposes a normalizing flow-based kernel prior (FKP) for kernel modeling in image super-resolution, which can improve the accuracy of kernel estimation and reduce parameters, runtime, and memory usage.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Meta-Transfer Learning for Zero-Shot Super-Resolution

Jae Woong Soh et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising

Haokui Zhang et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Runtime Network Routing for Efficient Image Classification

Yongming Rao et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

Kai Zhang et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning

Ke Yu et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing

Jian Zhang et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study

Eirikur Agustsson et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Add to Collection

Article Engineering, Electrical & Electronic

RAISR: Rapid and Accurate Image Super Resolution

Yaniv Romano et al.

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (2017)

Add to Collection

Article Mathematics, Applied

An iterative thresholding algorithm for linear inverse problems with a sparsity constraint

I Daubechies et al.

COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.