发布求助
文献互助 智能选刊 最新文献

2022 IEEE International Conference on Image Processing (ICIP)最新文献

筛选
英文 中文
SAR Image Super-Resolution Reconstruction Based on Full-Resolution Discrimination 基于全分辨率判别的SAR图像超分辨率重建
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897999
Guang-Xue Xiao, Long Zhang
{"title":"SAR Image Super-Resolution Reconstruction Based on Full-Resolution Discrimination","authors":"Guang-Xue Xiao, Long Zhang","doi":"10.1109/ICIP46576.2022.9897999","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897999","url":null,"abstract":"In image super-resolution reconstruction based on generative adversarial networks (GANs), the discrimination of high-resolution (HR) images enriches texture details. However, solely discriminating HR images limits the reconstruction quality, while discriminating other resolution features can improve the texture structures of the reconstructed HR images. Therefore, this paper proposes a SAR image super-resolution reconstruction algorithm based on full-resolution discrimination (FRD). In the suggested architecture, the full-resolution discriminator network is used to extract the high, medium, and low-resolution features, which are then fused into a full-resolution feature. Finally, the full-resolution feature difference between the authentic and fake images is input to the generator, which reduces the inaccuracy of single-resolution feature discrimination. Experimental results on synthetic aperture radar (SAR) images demonstrate that the proposed FRD algorithm performs better than the state-of-the-art super-resolution algorithms in reconstructing the texture structures of the HR SAR images.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128428826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Face Photo Synthesis Via Intermediate Semantic Enhancement Generative Adversarial Network 基于中间语义增强生成对抗网络的人脸照片合成
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897523
Haoxian Li, Jieying Zheng, Feng Liu
{"title":"Face Photo Synthesis Via Intermediate Semantic Enhancement Generative Adversarial Network","authors":"Haoxian Li, Jieying Zheng, Feng Liu","doi":"10.1109/ICIP46576.2022.9897523","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897523","url":null,"abstract":"Face sketch-photo synthesis is an important task in computer vision now. Recently, researchers have introduced face parsing to further improve the quality of synthesized face images. However, the semantic difference between face sketch parsing and photo parsing is usually ignored, leading to deformations and aliasing on synthesized face images. To solve these problems, we propose an intermediate face parsing to enhance the semantic information of the input face parsing. According to this intermediate face parsing, we propose an Intermediate Semantic Enhancement Generative Adversarial Network (ISEGAN) to generate high-quality realistic face photos. Furthermore, a Parsing Matching Loss (PM Loss) is proposed to encourage the intermediate face parsing to be more semantically accurate. Extensive comparison experiments demonstrate that our ISEGAN significantly out-performs the state-of-the-art methods.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129378018","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Stochastic Binary-Ternary Quantization for Communication Efficient Federated Computation 通信高效联邦计算的随机二元-三元量化
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897551
Rangu Goutham, Homayun Afrabandpey, Francesco Cricri, Honglei Zhang, Emre B. Aksu, M. Hannuksela, H. R. Tavakoli
{"title":"Stochastic Binary-Ternary Quantization for Communication Efficient Federated Computation","authors":"Rangu Goutham, Homayun Afrabandpey, Francesco Cricri, Honglei Zhang, Emre B. Aksu, M. Hannuksela, H. R. Tavakoli","doi":"10.1109/ICIP46576.2022.9897551","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897551","url":null,"abstract":"A stochastic binary-ternary (SBT) quantization approach is introduced for communication efficient federated computation; form of collaborative computing where locally trained models are exchanged between institutes. Communication of deep neural network models could be highly inefficient due to their large size. This motivates model compression in which quantization is an important step. Two well-known quantization algorithms are binary and ternary quantization. The first leads into good compression, sacrificing accuracy. The second provides good accuracy with less compression. To better benefit from trade-off between accuracy and compression, we propose an algorithm to stochastically switch between binary and ternary quantization. By combining with uniform quantization, we further extend the proposed algorithm to a hierarchical method which results in even better compression without sacrificing the accuracy. We tested the proposed algorithm using Neural network Compression Test Model (NCTM) provided by MPEG community. Our results demonstrate that the hierarchical variant of the proposed algorithm outperforms other quantization algorithms in term of compression, while maintaining the accuracy competitive to that provided by other methods.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127099546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Reference-Based Blind Super-Resolution Kernel Estimation 基于参考的盲超分辨率核估计
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897801
Mehmet Yamaç, Aakif Nawaz, Baran Ataman
{"title":"Reference-Based Blind Super-Resolution Kernel Estimation","authors":"Mehmet Yamaç, Aakif Nawaz, Baran Ataman","doi":"10.1109/ICIP46576.2022.9897801","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897801","url":null,"abstract":"Over the past few years, blind image super-resolution kernel estimation has become an emerging research topic. Re-cent SR kernel estimation works KernelGAN and FKP, as well as KernelNet, have shown promising results when applied to real-world SR problems. Among them, KernelNet improves the accuracy of SR kernel estimation while reducing computation time. Despite this, none of these previous studies addressed the estimation of SR kernel for scenarios that incorporate reference higher quality images. Our study presents KernelNet-R, a reference-based SR kernel estimator network. In both synthetically-generated pairs, as well as real-world pairs of images from wide-angle and telephoto camera images, the proposed solution reaches state-of-the-art (SoTa) kernel estimation performance.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127165766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advanced Motion Vector Difference Coding Beyond AV1 先进的运动矢量差分编码超越AV1
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897971
Liang Zhao, Xin Zhao, Shanchun Liu
{"title":"Advanced Motion Vector Difference Coding Beyond AV1","authors":"Liang Zhao, Xin Zhao, Shanchun Liu","doi":"10.1109/ICIP46576.2022.9897971","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897971","url":null,"abstract":"In AV1, for inter coded blocks with compound reference mode, motion vector differences (MVDs) are signaled for reference frame list 0 or list 1 separately with the same MVD precision regardless of the motion vector magnitude. In this paper, two advanced MVD coding methods are proposed. Firstly, to reduce the overhead for signaling MVD, the precision of the MVD is implicitly determined based on the associated MV class and MVD magnitude. Secondly, a new inter prediction mode is added to explore the correlation of MVDs between two reference frames, wherein one joint MVD is signaled for two reference frames. Experimental results demonstrate that, in the random-access common test condition luma coding gains of around 1.1% in terms of BD-rate can be achieved on top of a recent release of AOMedia Video Model (AVM).","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127194997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Egnet: A Novel Edge Guided Network for Instance Segmentation Egnet:一种新的边缘导向实例分割网络
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897497
Kaiwen Du, Xiao Wang, Y. Yan, Yang Lu, Hanzi Wang
{"title":"Egnet: A Novel Edge Guided Network for Instance Segmentation","authors":"Kaiwen Du, Xiao Wang, Y. Yan, Yang Lu, Hanzi Wang","doi":"10.1109/ICIP46576.2022.9897497","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897497","url":null,"abstract":"Edge information plays a significant role in instance segmentation. However, many instance segmentation methods directly perform pixel-wise classification via fully convolutional networks, which may ignore object edges. In this paper, we propose a novel Edge Guided Network (EGNet), which exploits edge information to improve the mask accuracy, for instance segmentation. Specifically, we propose an edge branch to extract edge information. Then, we use edge information as guidance and fuse it with mask features, in order to enrich the mask features. Furthermore, we propose a Spatial Attention (SA) module and add it to the backbone of our EGNet, enabling the network to focus more on foreground objects. In addition, we incorporate a Semantic Enhancement (SE) module into the edge branch, aiming to obtain additional global context information. Experimental results on the COCO 2017 dataset show the effectiveness of the proposed EGNet.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127502088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
End-To-End Depth Map Compression Framework Via Rgb-To-Depth Structure Priors Learning 基于Rgb-To-Depth结构先验学习的端到端深度图压缩框架
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9898073
Minghui Chen, Pingping Zhang, Z. Chen, Yun Zhang, Xu Wang, S. Kwong
{"title":"End-To-End Depth Map Compression Framework Via Rgb-To-Depth Structure Priors Learning","authors":"Minghui Chen, Pingping Zhang, Z. Chen, Yun Zhang, Xu Wang, S. Kwong","doi":"10.1109/ICIP46576.2022.9898073","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9898073","url":null,"abstract":"In this paper, we propose a novel framework to exploit and utilize the shared information inner RGB-D data for efficient depth map compression. Two main codecs, designed based on the existing end-to-end image compression network, are adopted for RGB image compression and enhanced depth image compression with RGB-to-Depth structure prior, respectively. In particular, we propose a Structure Prior Fusion (SPF) module to extract the structure information from both RGB and depth codecs at multi-scale feature levels and fuse the cross-modal feature to generate more efficient structure priors for depth compression. Extensive experiments show that the proposed framework can achieve competitive rate-distortion performance as well as RGB-D task-specific performance at depth map compression compared with the direct compression scheme.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130146248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultra-Low Bitrate Video Conferencing Using Deep Image Animation 使用深度图像动画的超低比特率视频会议
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897526
Goluck Konuko, G. Valenzise, Stéphane Lathuilière
{"title":"Ultra-Low Bitrate Video Conferencing Using Deep Image Animation","authors":"Goluck Konuko, G. Valenzise, Stéphane Lathuilière","doi":"10.1109/ICIP46576.2022.9897526","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897526","url":null,"abstract":"In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely limited, we adopt a model-based approach that employs deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side. The overall system is trained in an end-to-end fashion minimizing a reconstruction error on the encoder output. Objective and subjective quality evaluation experiments demonstrate that the proposed approach provides an average bitrate reduction for the same visual quality of more than 60% compared to HEVC.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130782162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Switchable CNN-Based Same-Resolution and Super-Resolution In-Loop Restoration for Next Generation Video Codecs 可切换的基于cnn的同分辨率和超分辨率在环恢复下一代视频编解码器
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897763
Urvang Joshi, Yue Chen, D. Mukherjee, O. Guleryuz, Sha Li, In Suk Chong
{"title":"Switchable CNN-Based Same-Resolution and Super-Resolution In-Loop Restoration for Next Generation Video Codecs","authors":"Urvang Joshi, Yue Chen, D. Mukherjee, O. Guleryuz, Sha Li, In Suk Chong","doi":"10.1109/ICIP46576.2022.9897763","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897763","url":null,"abstract":"We present a common framework for in-loop same-resolution and super-resolution restoration for incorporation into a next-generation video codec. Building on the in-loop filtering pipeline in the AV1 video codec from the Alliance for Open Media (AOM), we first enhance it to support symmetric spatial down-up scaling with better down and upscaling filters, followed by adding switchable frame-level CNNs to restore the reconstructed frames. Furthermore, the architectures for the CNNs used are constrained to be very simple with a relatively small number of parameters and multiply-add operations per decoded pixel to make them practically feasible in hardware. Preliminary results are presented on test sets being used by AOM for their ongoing next-generation video codec (AV2) development effort.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132487922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Non-Smooth Energy Dissipating Networks 非光滑能量耗散网络
2022 IEEE International Conference on Image Processing (ICIP) Pub Date : 2022-10-16 DOI: 10.1109/ICIP46576.2022.9897173
Hannah Dröge, T. Möllenhoff, Michael Möller
{"title":"Non-Smooth Energy Dissipating Networks","authors":"Hannah Dröge, T. Möllenhoff, Michael Möller","doi":"10.1109/ICIP46576.2022.9897173","DOIUrl":"https://doi.org/10.1109/ICIP46576.2022.9897173","url":null,"abstract":"Over the past decade, deep neural networks have been shown to perform extremely well on a variety of image reconstruction tasks. Such networks do, however, fail to provide guarantees about these predictions, making them difficult to use in safety-critical applications. Recent works addressed this problem by combining model-and learning-based approaches, e.g., by forcing networks to iteratively minimize a model-based cost function via the prediction of suitable descent directions. While previous approaches were limited to continuously differentiable cost functions, this paper discusses a way to remove the restriction of differentiability. We propose to use the Moreau-Yosida regularization of such costs to make the framework of energy dissipating networks applicable. We demonstrate our framework on two exemplary applications, i.e., safeguarding energy dissipating denoising networks to the expected distribution of the noise as well as enforcing binary constraints on bar-code deblurring networks to improve their respective performances.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130835739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信