Filters








1,066 Hits in 4.3 sec

Region-Adaptive Dense Network for Efficient Motion Deblurring

Kuldeep Purohit, A. N. Rajagopalan
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This capability is complemented by a self-attentive module which captures non-local spatial relationships among the intermediate features and enhances the spatially varying processing capability.  ...  Our network facilitates interpretable modeling of the spatially-varying deblurring process while dispensing with multi-scale processing and large filters entirely.  ...  Conclusions We proposed an efficient motion deblurring architecture composed of convolutional modules that enable spatially adaptive feature learning through filter transformations and feature attention  ... 
doi:10.1609/aaai.v34i07.6862 fatcat:pu6mz3jasfexnidcg3rawsrf5q

Motion Deblurring with an Adaptive Network [article]

Kuldeep Purohit, A. N. Rajagopalan
2022 arXiv   pre-print
Our networks can implicitly model the spatially-varying deblurring process, while dispensing with multi-scale processing and large filters entirely.  ...  This capability is complemented by a self-attentive module which captures non-local relationships among the intermediate features and enhances the receptive field.  ...  Conclusions We proposed efficient image and video deblurring architectures composed of convolutional modules that enable spatially adaptive feature learning through filter transformations and feature attention  ... 
arXiv:1903.11394v4 fatcat:jgsssxep6vfbnafshrg2x6ijke

Adaptive Single Image Deblurring [article]

Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan
2022 arXiv   pre-print
In this work, we propose an efficient pixel adaptive and feature attentive design for handling large blur variations within and across different images.  ...  We use a patch hierarchical attentive architecture composed of the above module that implicitly discover the spatial variations in the blur present in the input image and in turn perform local and global  ...  We propose an efficient deblurring design built on new convolutional modules that learn transformation of features using global attention and dynamic local filters.  ... 
arXiv:2201.00155v1 fatcat:jexcg67nqfgefi63zja27aj2xe

Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring [article]

Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan
2020 arXiv   pre-print
In this work, we propose an efficient pixel adaptive and feature attentive design for handling large blur variations across different spatial locations and process each test image adaptively.  ...  This paper tackles the problem of motion deblurring of dynamic scenes.  ...  The major contributions of this work are: • We propose an efficient deblurring design built on new convolutional modules that learn the transformation of features using global attention and adaptive local  ... 
arXiv:2004.05343v1 fatcat:jhsglmlubzb5ja4s7omfxasfo4

Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring

Maitreya Suin, Kuldeep Purohit, A. N. Rajagopalan
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we propose an efficient pixel adaptive and feature attentive design for handling large blur variations across different spatial locations and process each test image adaptively.  ...  This paper tackles the problem of motion deblurring of dynamic scenes.  ...  The major contributions of this work are: • We propose an efficient deblurring design built on new convolutional modules that learn the transformation of features using global attention and adaptive local  ... 
doi:10.1109/cvpr42600.2020.00366 dblp:conf/cvpr/SuinPR20 fatcat:rv6ptq2x35g5phvepetqe3qkqi

Flow-Guided Sparse Transformer for Video Deblurring [article]

Jing Lin, Yuanhao Cai, Xiaowan Hu, Haoqian Wang, Youliang Yan, Xueyi Zou, Henghui Ding, Yulun Zhang, Radu Timofte, Luc Van Gool
2022 arXiv   pre-print
In this paper, we propose a novel framework, Flow-Guided Sparse Transformer (FGST), for video deblurring.  ...  Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring.  ...  Acknowledgements: This work is partially supported by the NSFC fund (61831014), the Shenzhen Science and Technology Project under Grant (CJGJZD20200617102601004, JSGG20210802153150005).  ... 
arXiv:2201.01893v3 fatcat:pg5w2bndbngydl2ynjek4x4rja

Single Image Joint Motion Deblurring and Super-Resolution Using the Multi-Scale Channel Attention Modules

Misak T. Shoyan, National Polytechnic University of Armenia
2021 Mathematical Problems of Computer Science  
The implementation code and the pre-trained model are publicly available at https://github.com/misakshoyan/joint-motion-deblur-and-sr.  ...  The deblurring subnetwork is based on multi-stage progressive architecture, while the super-resolution subnetwork is designed using the multi-scale channel attention modules.  ...  To solve the motion deblurring and SR problems jointly, the network should extract both contextually and spatially informative features.  ... 
doi:10.51408/1963-0076 fatcat:ulnois4kvzggvclqywynfcfcfy

Stripformer: Strip Transformer for Fast Image Deblurring [article]

Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin
2022 arXiv   pre-print
reweight image features in the horizontal and vertical directions to catch blurred patterns with different orientations.  ...  In addition to detecting region-specific blurred patterns of various orientations and magnitudes, Stripformer is also a token-efficient and parameter-efficient transformer model, demanding much less memory  ...  Hence, transformers with multi-head self-attention to explore local and global correlations would be a good choice for deblurring.  ... 
arXiv:2204.04627v2 fatcat:xqdoryx4ufcjreoaqwhu2bwt2e

NTIRE 2020 Challenge on Image and Video Deblurring

Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee, Yu Tseng, Yu-Syuan Xu, Cheng-Ming Chiang, Yi-Min Tsai, Stephan Brehm, Sebastian Scherer, Dejia Xu, Yihao Chu (+36 others)
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring.  ...  The winning methods demonstrate the state-ofthe-art performance on image and video deblurring tasks.  ...  ., DisneyResearch|Studios, and ETH Zurich (Computer Vision Lab).  ... 
doi:10.1109/cvprw50498.2020.00216 dblp:conf/cvpr/NahSTLTXCTBSXCS20 fatcat:a6ojyfuidrbb3avwdpv4mje77e

Restormer: Efficient Transformer for High-Resolution Image Restoration [article]

Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang
2022 arXiv   pre-print
While the Transformer model mitigates the shortcomings of CNNs (i.e., limited receptive field and inadaptability to input content), its computational complexity grows quadratically with the spatial resolution  ...  In this work, we propose an efficient Transformer model by making several key designs in the building blocks (multi-head attention and feed-forward network) such that it can capture long-range pixel interactions  ...  Special thanks to Abdullah Abuolaim and Zhendong Wang for providing the results.  ... 
arXiv:2111.09881v2 fatcat:zzmue7de3feergl5ciry25r3qm

NTIRE 2019 Challenge on Video Deblurring: Methods and Results

Seungjun Nah, Radu Timofte, Sungyong Baik, Seokil Hong, Gyeongsik Moon, Sanghyun Son, Kyoung Mu Lee, Xintao Wang, Kelvin C.K. Chan, Ke Yu, Chao Dong, Chen Change Loy (+33 others)
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
This paper reviews the first NTIRE challenge on video deblurring (restoration of rich details and high frequency components from blurred video frames) with focus on the proposed solutions and results.  ...  Track 1 employed dynamic motion blurs while Track 2 had additional MPEG video compression artifacts. Each competition had 109 and 93 registered participants.  ...  ., and ETH Zurich.  ... 
doi:10.1109/cvprw.2019.00249 dblp:conf/cvpr/NahTBHMSL19 fatcat:eieq2a6ms5bn7hx6cpccozhuyi

NTIRE 2020 Challenge on Image and Video Deblurring [article]

Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee
2020 arXiv   pre-print
Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring.  ...  The winning methods demonstrate the state-ofthe-art performance on image and video deblurring tasks.  ...  ., DisneyResearch|Studios, and ETH Zurich (Computer Vision Lab).  ... 
arXiv:2005.01244v2 fatcat:aoy3tyxlybefrd7yd5ywvr6jh4

Efficient Video Deblurring Guided by Motion Magnitude [article]

Yusheng Wang and Yunfan Lu and Ye Gao and Lin Wang and Zhihang Zhong and Yinqiang Zheng and Atsushi Yamashita
2022 arXiv   pre-print
The MMP consists of both spatial and temporal blur level information, which can be further integrated into an efficient recurrent neural network (RNN) for video deblurring.  ...  Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur.  ...  Acknowledgements This paper is supported by JSPS KAKENHI Grant Numbers 22H00529 and 20H05951.  ... 
arXiv:2207.13374v1 fatcat:7r2me7362bad5a5agmddddwfbq

Attention Network for Non-Uniform Deblurring

Qing Qi, Jichang Guo, Weipei Jin
2020 IEEE Access  
In this paper, we propose a solution to transform spatially variant blurry images into the photo-realistic sharp manifold. In this paper, we investigate an attention network for image deblurring.  ...  Therefore, we propose a novel dense feature fusion block that consists of a channel attention module and a pixel attention module.  ...  Specifically, each attention block contains spatial attention module and channel attention module.  ... 
doi:10.1109/access.2020.2997408 fatcat:oyis2k6zx5bvxembvkibpc7f5q

Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency [article]

Dong Huo, Abbas Masoumzadeh, Yee-Hong Yang
2022 arXiv   pre-print
Hence, non-uniform motion deblurring is still a challenging and open problem.  ...  Many deep learning based methods are designed to remove non-uniform (spatially variant) motion blur caused by object motion and camera shake without knowing the blur kernel.  ...  In addition to the above model, some works model the non-uniform motion deblurring as a linear transformation. Indeed, Bahat et al.  ... 
arXiv:2106.14336v2 fatcat:67okpikuzzfzxpu7nvgzu2gpvu
« Previous Showing results 1 — 15 out of 1,066 results