检索结果-内蒙古大学图书馆

Two-stage Parallax Correction and Multi-stage Cross-view Fusion Network Based Stereo image Super-Resolution

Two-stage Parallax Correction and Multi-stage Cross-view Fus...

IEEE International conference on visual communications and image processing (VCIP) - visual communications in the Era of AI and Limited Resources

作者： Zheng, Yijian Li, Sumei Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China

ISBN: (纸本)9781728185514

Stereo image super-resolution (SR) has achieved great progress in recent years. However, the two major problems of the existing methods are that the parallax correction is insufficient and the cross-view information fusion only occurs in the beginning of the network. To address these problems, we propose a two-stage parallax correction and a multi-stage cross-view fusion network for better stereo image SR results. Specially, the two-stage parallax correction module consists of horizontal parallax correction and refined parallax correction. The first stage corrects horizontal parallax by parallax attention. The second stage is based on deformable convolution to refine horizontal parallax and correct vertical parallax simultaneously. Then, multiple cascaded enhanced residual spatial feature transform blocks are developed to fuse cross-view information at multiple stages. Extensive experiments show that our method achieves state-of-the-art performance on the KITTI2012, KITTI2015, Middlebury and Flickr1024 datasets.

关键词： Stereo image super-resolution Parallax correction Multi-stage cross-view fusion

来源：评论

学校读者我要写书评

暂无评论

Motion tracking of color image sequences using neural networks

Motion tracking of color image sequences using neural networ...

引用

1997 conference on visual communications and image processing

作者： Iwata, H Nagahashi, H Tokyo Institute of Technology (Japan)

ISBN: (纸本)0819424358

Region segmentation of images is a well-known 'ill-posed problem', and a specific algorithm like regularization seems to be available. In this paper, an active region segmentation algorithm based on a regularization approach using the Hopfield neural network is proposed. The objective function to be minimized by the network is defined based on the criteria that integrate region growing and edge detection for the image segmentation. The energy of the network tends to converge on a local minimum, so that pyramid images are used to avoid such local minima and to achieve fast convergence. Moreover, the active region segmentation algorithm is applied to a sequence of color images to track an object region that change in appearance through complex and nonstationary background/foreground situations. Experimental results show that it's possible to segment images and track the object region using the minimization principle of the energy function of the Hopfield neural network.

关键词： motion tracking color image sequences active region segmentation Hopfield neural network

来源：评论

学校读者我要写书评

暂无评论

Robust embedded zerotree wavelet coding algorithm

Robust embedded zerotree wavelet coding algorithm

引用

visual communications and image processing 1998 conference

作者： Thillainathan, S Bull, D Canagarajah, N Univ Bristol Ctr Commun Res Image Commun Grp Bristol BS8 1UB Avon England

ISBN: (纸本)0819427497

Error-resilience is an important feature of any image or video coding algorithm associated with transmission over noisy or multipath channels. in this paper, we present a robust coding algorithm based on a modified version of the zerotree coding technique, The algorithm provides significantly improved error-resilience with minimum added redundancy while still. retaining the efficiency and scalability of tile original technique.

关键词： zerotree algorithm error-resilient coding scalability 3-D wavelet coding

来源：评论

学校读者我要写书评

暂无评论

Learning from the NN-based Compressed Domain with Deep Feature Reconstruction Loss

Learning from the NN-based Compressed Domain with Deep Featu...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Chen, Liuhong Sun, Heming Zeng, Xiaoyang Fan, Yibo Fudan Univ Shanghai Peoples R China Waseda Univ Tokyo Japan JST PRESTO Saitama Japan

ISBN: (纸本)9781665475921

To speedup the image classification process which conventionally takes the reconstructed images as input, compressed domain methods choose to use the compressed images without decompression as input. Correspondingly, there will be a certain decline about the accuracy. Our goal in this paper is to raise the accuracy of compressed domain classification method using compressed images output by the NN-based image compression networks. Firstly, we design a hybrid objective loss function which contains the reconstruction loss of deep feature map. Secondly, one image reconstruction layer is integrated into the image classification network for up-sampling the compressed representation. These methods greatly help increase the compressed domain image classification accuracy and need no extra computational complexity. Experimental results on the benchmark imageNet prove that our design outperforms the latest work ResNet-41 with a large accuracy gain, about 4.49% on the top-1 classification accuracy. Besides, the accuracy lagging behinds the method using reconstructed images is also reduced to 0.47%. Moreover, our designed classification network has the lowest computational complexity and model complexity.

关键词： Compressed domain image analysis image classification LIC (Learned image Compression) feature reconstruction

来源：评论

学校读者我要写书评

暂无评论

Model supported exploitation of aerial images

Model supported exploitation of aerial images

引用

1997 conference on visual communications and image processing

作者： Chellappa, R UNIV MARYLAND CTR AUTOMAT RESCOLLEGE PKMD 20742

ISBN: (纸本)0819424358

Model-supported exploitation is a new paradigam in image Understanding research. In this paradigm, three main technical areas have been identified: semi-automatic or automatic construction of site models, automated positioning of images to the sites, and monitoring of movable objects and construction activities. In this paper, we summarize recent progress in the detection and counting of vehicles in selected locales, monitoring and characterization of vehicle groupings. We present the algorithms used and the results obtained, The detection and counting method employs geometrical models and uses a spatial contour matching approach. The configuration detection method exploits knowledge of geometrical models in the frequency domain. The issues of parameter learning as well as sensitivity of the detection performance to misspecification of model and tuning parameters are briefly examined.

关键词： 3D modeling Data modeling Roads Sensors Detection and tracking algorithms Fourier transforms Cameras image processing Performance modeling image understanding

来源：评论

学校读者我要写书评

暂无评论

Lookup Register-Tables with Interpolation for Effective image Transformation on x86/64 CPUs

Lookup Register-Tables with Interpolation for Effective Imag...

引用

2024 conference on visual communications and image processing

作者： Kamei, Hirokazu Honda, Soichiro Hayashi, Kohei Maeda, Yoshihiro Fukushima, Norishige Nagoya Inst Technol Grad Sch Engn Nagoya Aichi Japan Shibaura Inst Technol Coll Engn Tokyo Japan

ISBN: (纸本)9798331529543;9798331529550

Lookup tables (LUTs) are commonly used to speed up image processing by handling complex mathematical functions like sine and exponential calculations. They are used in various applications such as camera image processing, high-dynamic range imaging, and edge-preserving filtering. However, due to the increasing gap between computing and input/output performance, LUTs are becoming less effective. Even though specific circuits like SIMD can improve LUT efficiency, they still need to bridge the performance gap fully. The gap makes it difficult to choose between direct numerical and LUT calculations. For this problem, a register-LUTs method with the nearest neighbor was proposed;however, it is limited for functions with narrow-range values approaching zero. In this paper, we propose a method for using register LUTs to process images efficiently over a wide range of values. Our contributions include proposing register-LUT with linear interpolation for efficient computation, using a smaller data type for further efficiency, and suggesting an efficient data retrieving method.

关键词： SIMD register-LUT interpolation x86/64 CPU image processing

来源：评论

学校读者我要写书评

暂无评论

Improving Latent Quantization of Learned image Compression with Gradient Scaling

Improving Latent Quantization of Learned Image Compression w...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Sun, Heming Yu, Lu Katto, Jiro Waseda Univ Waseda Res Inst Sci & Engn Tokyo Japan Zhejiang Univ Inst Informat & Commun Engn Hangzhou Peoples R China JST PRESTO 4-1-8 Honcho Kawaguchi Saitama Japan Waseda Univ Dept Comp Sci & Commun Engn Tokyo Japan

ISBN: (纸本)9781665475921

Learned image compression (LIC) has shown its superior compression ability. Quantization is an inevitable stage to generate quantized latent for the entropy coding. To solve the non-differentiable problem of quantization in the training phase, many differentiable approximated quantization methods have been proposed. However, the derivative of quantized latent to non-quantized latent are set as one in most of the previous methods. As a result, the quantization error between non-quantized and quantized latent is not taken into consideration in the gradient descent. To address this issue, we exploit the gradient scaling method to scale the gradient of non-quantized latent in the back-propagation. The experimental results show that we can outperform the recent LIC quantization methods.

关键词： Learned image compression Quantization Gradient scaling

来源：评论

学校读者我要写书评

暂无评论

DCTResNet: Transform Domain image Deblocking for Motion Blur images

DCTResNet: Transform Domain Image Deblocking for Motion Blur...

引用

IEEE International conference on visual communications and image processing (VCIP) - visual communications in the Era of AI and Limited Resources

作者： Maharjan, Paras Xu, Ning Xu, Xuan Song, Yuyan Li, Zhu Univ Missouri Kansas City MO 64110 USA Kwai Inc Palo Alto CA USA

ISBN: (纸本)9781728185514

Pixel recovery with deep learning has shown to be very effective for a variety of low-level vision tasks like image super-resolution, denoising, and deblurring. Most existing works operate in the spatial domain, and there are few works that exploit the transform domain for image restoration tasks. In this paper, we present a transform domain approach for image deblocking using a deep neural network called DCTResNet. Our application is compressed video motion deblur, where the input video frame has blocking artifacts that make the deblurring task very challenging. Specifically, we use a block-wise Discrete Cosine Transform (DCT) to decompose the image into its low and high-frequency sub-band images and exploit the strong subband specific features for more effective deblocking solutions. Since JPEG also uses DCT for image compression, using DCT sub-band images for image deblocking helps to learn the JPEG compression prior to effectively correct the blocking artifacts. Our experimental results show that both PSNR and SSIM for DCTResNet perform more favorably than other state-of-the-art (SOTA) methods, while significantly faster in inference time.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Perceptual image Compression With Conditional Diffusion Transformers

Perceptual Image Compression With Conditional Diffusion Tran...

引用

2024 conference on visual communications and image processing

作者： Mao, Rui Feng, Xinmin Gao, Changsheng Li, Li Liu, Dong Sun, Xiaoyan Univ Sci & Technol China MOE Key Lab Brain Inspired Intelligent Percept & Hefei Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Generative models have significantly advanced generative AI, particularly in image and video generation. Recognizing their potential, researchers have begun exploring their application in image compression. However, existing methods face two primary challenges: limited performance improvement and high model complexity. In this paper, to address these two challenges, we propose a perceptual image compression solution by introducing a conditional diffusion model. Given that compression performance heavily depends on the decoder's generative capability, we base our decoder on the diffusion transformer architecture. To address the model complexity problem, we implement the diffusion transformer architecture with Swin transformer. Equipped with enhanced generative capability, we further augment the decoder with informative features using a multi-scale feature fusion module. Experimental results demonstrate that our approach surpasses existing perceptual image compression methods while achieving lower model complexity.

关键词： Diffusion transformer (DiT) image generation perceptual image compression Swin transformer

来源：评论

学校读者我要写书评

暂无评论

Generation of arbitrarily focused images by using multiple differently focused images

引用

JOURNAL OF ELECTRONIC IMAGING 1998年第1期7卷 138-144页

作者： Kodama, K Aizawa, K Hatori, M Univ Tokyo Dept Elect Engn Tokyo 113 Japan

We propose a novel method of arbitrarily focused image generation using multiple differently focused images. First, we describe our previously proposed select and merge method for all focused image acquisition. We can get good results by using this method but it is not easy to extend this method for generating arbitrarily focused images. Then, based on the assumption that depth of a scene changes stepwise, we derive a formula for reconstruction between the desired arbitrarily focused image and multiple acquired images;we can reconstruct the arbitrarily focused image by iterative use of the formula. We also introduce coarse-to-fine estimation of point spread functions (PSFs) of the acquired images. We reconstruct arbitrarily focused images for a natural scene. In other words, we simulate virtual cameras and generate images focused on arbitrary depths. (C) 1998 SPIE and IS&T. [S1017-9909(98)02201-6].

关键词： Cameras image acquisition Point spread functions

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：