Filters








2,046 Hits in 9.4 sec

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results [article]

Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha (+51 others)
2020 arXiv   pre-print
The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images.  ...  The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.  ...  Acknowledgements We thank the NTIRE 2020 sponsors: HUAWEI, OPPO, Voyage81, MediaTek, DisneyResearch|Studios, and Computer Vision Lab (CVL) ETH Zurich.  ... 
arXiv:2005.01056v1 fatcat:6nwj5ilbgbgjnmd6oy435hjdhi

Modified Dual Path Network With Transform Domain Data For Image Super-Resolution

De-Wei Chen, Chih-Hung Kuo
2020 IEEE Access  
Recently, studies on single image super-resolution using Deep Convolutional Neural Networks (DCNN) have been demonstrated to have made outstanding progress over conventional signal-processing based methods  ...  INDEX TERMS Super resolution, deep learning, convolutional neural network.  ...  DEEP LEARNING BASED IMAGE SUPER-RESOLUTION The strong feature extraction and data representation abilities in deep learning have led to a surge of research on convolutional neural networks for SISR.  ... 
doi:10.1109/access.2020.2997028 fatcat:etllfwvjnjgldggq5sebpmtmoy

A comprehensive review of deep learning-based single image super-resolution

Syed Muhammad Arsalan Bashir, Yi Wang, Mahrukh Khan, Yilong Niu
2021 PeerJ Computer Science  
), recurrent back-projection network (RBPN), second-order attention network (SAN), SR feedback network (SRFBN) and the wavelet-based residual attention network (WRAN).  ...  for image super-resolution.  ...  Four main categories are (a) classical methods of image super-resolution, (b) deep learning-based methods for SR, (c) applications of super-resolution, (d) future research and directions in SR.  ... 
doi:10.7717/peerj-cs.621 fatcat:jsd6fw3ewjeudgnypdam7xy5oy

Multiscale Recursive Feedback Network for Image Super-Resolution

Xiao Chen, Chaowen Sun
2022 IEEE Access  
A multiscale recursive feedback network (MSRFN) for image super-resolution is proposed.  ...  Deep learning-based networks have achieved great success in the field of image superresolution.  ...  CONCLUSION We propose a multiscale recursive feedback network for image super-resolution.  ... 
doi:10.1109/access.2022.3142510 fatcat:kxdgelfojbe3xba7kfau7wdnvm

Feedback Network for Image Super-Resolution [article]

Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu
2019 arXiv   pre-print
Recent advances in image super-resolution (SR) explored the power of deep learning to achieve a better reconstruction performance.  ...  In addition, we introduce a curriculum learning strategy to make the network well suitable for more complicated tasks, where the low-resolution images are corrupted by multiple types of degradation.  ...  Related Work Deep learning based image super-resolution Deep learning has shown its superior performance in various computer vision tasks including image SR. Dong et al.  ... 
arXiv:1903.09814v2 fatcat:ulhq4umsgve47kcb2wcgzceofy

Efficient and High-Quality Monocular Depth Estimation via Gated Multi-Scale Network

Lixiong Lin, Guohui Huang, Yanjie Chen, Liwei Zhang, Bingwei He
2020 IEEE Access  
At present, most of the monocular depth estimation methods based on deep learning manipulate images at low resolution that leads to loss of detail and blurring of boundaries.  ...  To improve the depth map quality and reduce the running time of the network, we introduce super-resolution techniques as methods of up-sampling to generate high-quality depth images at a faster rate for  ...  [37] applied a very deep convolutional network to learn residuals for accurate image SR.  ... 
doi:10.1109/access.2020.2964733 fatcat:liab7udu2vhqrgrhodysjw6oxu

Generative Adversarial Networks for Image Super-Resolution: A Survey [article]

Chunwei Tian, Xuanyu Zhang, Jerry Chun-Wen Lin, Wangmeng Zuo, Yanning Zhang
2022 arXiv   pre-print
Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised  ...  Single image super-resolution (SISR) has played an important role in the field of image processing.  ...  To obtain a better and more efficient SR model, a variety of deep learning methods were applied to a large-scale image dataset to solve the super-resolution tasks.  ... 
arXiv:2204.13620v1 fatcat:hlwdqith65cxrbqrnbphjz6u4u

Transformers in Vision: A Survey [article]

Salman Khan, Muzammal Naseer, Munawar Hayat, Syed Waqas Zamir, Fahad Shahbaz Khan, Mubarak Shah
2021 arXiv   pre-print
We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional encoding.  ...  to very large capacity networks and huge datasets.  ...  ), Alex Meinke (Uni-Tuebingen), Irwan Bello (Google Brain) and Manoj Kumar (Google Brain) for their helpful feedback on the survey.  ... 
arXiv:2101.01169v4 fatcat:ynsnfuuaize37jlvhsdki54cy4

Are we ready for a new paradigm shift? A Survey on Visual Deep MLP [article]

Ruiyang Liu, Yinghui Li, Linmi Tao, Dun Liang, Hai-Tao Zheng
2022 arXiv   pre-print
We compare the intrinsic connections and differences between convolution, self-attention mechanism, and Token-mixing MLP in detail.  ...  Advantages and limitations of Token-mixing MLP are provided, followed by careful analysis of recent MLP-like variants, from module design to network architecture, and their applications.  ...  Acknowledgments We acknowledge and deeply appreciate all the feedback and comments provided by the editors and the panel of anonymous reviewers.  ... 
arXiv:2111.04060v6 fatcat:xgqbdicbl5fjxh52ouopyhmayq

On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey [article]

Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia
2021 arXiv   pre-print
based on deep networks.  ...  In this paper, we review recent research in the field of learning-based depth estimation from single and binocular images highlighting the synergies, the successes achieved so far and the open challenges  ...  To address this, Pillai et al. introduce a deep neural network relying on techniques typically used for super-resolution.  ... 
arXiv:2004.08566v2 fatcat:wcwfgzibo5evbkun3atpsz6kwm

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution [article]

Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han
2020 arXiv   pre-print
To explore the spectrum of efficient 3D models, we first define a flexible architecture design space based on SPVConv, and we then present 3D Neural Architecture Search (3D-NAS) to search the optimal network  ...  With negligible overhead, this point-based branch is able to preserve the fine details even from large outdoor scenes.  ...  We thank Nick Stathas and Yue Dong for their feedback on the draft. This work is supported by MIT Quest for Intelligence, MIT-IBM Watson AI Lab, Xilinx and Samsung.  ... 
arXiv:2007.16100v2 fatcat:omt5fknvsndhlboulnvy6chh2i

Modality specific U-Net variants for biomedical image segmentation: A survey [article]

Narinder Singh Punn, Sonali Agarwal
2022 arXiv   pre-print
With the advent of advancements in deep learning approaches, such as deep convolution neural network, residual neural network, adversarial network; U-Net architectures are most widely utilized in biomedical  ...  In recent studies, U-Net based approaches have illustrated state-of-the-art performance in different applications for the development of computer-aided diagnosis systems for early diagnosis and treatment  ...  Acknowledgment We thank our institute, Indian Institute of Information Technology Allahabad (IIITA), India and Big Data Analytics (BDA) lab for allocating the necessary  ... 
arXiv:2107.04537v4 fatcat:m5oqea5q6vhbhkerjmejder3hu

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
Results are presented for various challenging cases for some large-scale public datasets.  ...  Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision.  ...  The stacking of convolution and pooling operation in deep CNNs allows the receptive field of the network to grow gradually with depth.  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga

A Survey of Visual Transformers [article]

Yang Liu, Yao Zhang, Yixin Wang, Feng Hou, Jin Yuan, Jiang Tian, Yang Zhang, Zhongchao Shi, Jianping Fan, Zhiqiang He
2022 arXiv   pre-print
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP).  ...  segmentation) as well as multiple sensory data stream (images, point clouds, and vision-language data).  ...  In the future, we anticipate that the Transformer backbone would cooperate with the deep high-resolution network to solve dense prediction tasks. VI.  ... 
arXiv:2111.06091v3 fatcat:a3fq6lvvzzgglb3qtus5qwrwpe

S CNet: Monocular Depth Completion for Autonomous Systems and 3D Reconstruction [article]

Lei Zhang, Weihai Chen, Chao Hu, Xingming Wu, Zhengguo Li
2019 arXiv   pre-print
Dense depth completion is essential for autonomous systems and 3D reconstruction.  ...  In this paper, a lightweight yet efficient network (S\&CNet) is proposed to obtain a good trade-off between efficiency and accuracy for the dense depth completion.  ...  Then, the enhanced features are feed into the decoder, which consists of three up-projection units as introduced in [6] to gradually increase the feature resolution.  ... 
arXiv:1907.06071v2 fatcat:xkjf776psjahdbylpfm26aeyu4
« Previous Showing results 1 — 15 out of 2,046 results