检索结果-内蒙古大学图书馆

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Xinyi Zhao, Weiyue Liu, Tianqi Huang, Zihao Cao, Zhiguo Li, Xin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Albany AlbanyNY12222 United States

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS. Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

Transmission-Constrained Consensus of Multiagent Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiaotian Su, Housheng School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

This paper studies the consensus problem for multiagent systems with transmission constraints. A novel model of multiagent systems is proposed where the information transmissions between agents are disturbed by irregular distortions or interferences (named transmission constraint functions), and this model is universal which can be applied in many cases, such as interval consensus and discarded consensus. In the transmission-constrained consensus problem, we obtain the necessary and sufficient condition that agents can converge to state consensus. Furthermore, a more general case is studied in which the system reaches an equilibrium. Based on some techniques of algebraic topology and stability theory, the existence, uniqueness and stability of the system equilibrium point can be proven, which means the system can reach an asymptotically stable equilibrium. Moreover, the state values of the equilibrium are only decided by the network structure and transmission constraint functions, but not the agents’ initial states. Finally, numerical simulations are presented to illustrate the proposed theorems and corollaries. © 2022, CC BY-NC-SA.

关键词： Directed graphs

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Zhiyu Chen, Yinpeng Zhang, Jiale Lu, Hao Cao, Zhiguo Zhong, Weicai Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei CBG Consumer Cloud Service Search Product & Big Data Platform Department China

Automatic image cropping algorithms aim to recompose images like human-being photographers by generating the cropping boxes with improved composition quality. Cropping box regression approaches learn the beauty of composition from annotated cropping boxes. However, the bias of annotations leads to quasi-trivial recomposing results, which has an obvious tendency to the average location of training samples. The crux of this predicament is that the task is naively treated as a box regression problem, where rare samples might be dominated by normal samples, and the composition patterns of rare samples are not well exploited. Observing that similar composition patterns tend to be shared by the cropping boundaries annotated nearly, we argue to find the beauty of composition from the rare samples by clustering the samples with similar cropping boundary annotations, i.e., similar composition patterns. We propose a novel Contrastive Composition Clustering (C2C) to regularize the composition features by contrasting dynamically established similar and dissimilar pairs. In this way, common composition patterns of multiple images can be better summarized, which especially benefits the rare samples and endows our model with better generalizability to render nontrivial results. Extensive experimental results show the superiority of our model compared with prior arts. We also illustrate the philosophy of our design with an interesting analytical visualization. Copyright © 2023, The Authors. All rights reserved.

关键词： image enhancement

Fast Full-frame Video Stabilization with Iterative Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Li, Xin Peng, Zhan Luo, Xianrui Ye, Xinyi Lu, Hao Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Albany AlbanyNY12222 United States

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Xingyi Hong, Chaoyi Wang, Yiran Cao, Zhiguo Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China S-Lab Nanyang Technological University Singapore

We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in self-occluded areas. This is because a single view only provides limited information. We observe that man-made objects usually exhibit symmetric appearances, which introduce additional prior knowledge. Motivated by this, we investigate the potential performance gains of explicitly embedding symmetry into the scene representation. In this paper, we propose SymmNeRF, a neural radiance field (NeRF) based framework that combines local and global conditioning under the introduction of symmetry priors. In particular, SymmNeRF takes the pixel-aligned image features and the corresponding symmetric features as extra inputs to the NeRF, whose parameters are generated by a hypernetwork. As the parameters are conditioned on the image-encoded latent codes, SymmNeRF is thus scene-independent and can generalize to new scenes. Experiments on synthetic and real-world datasets show that SymmNeRF synthesizes novel views with more details regardless of the pose transformation, and demonstrates good generalization when applied to unseen objects. Code is available at: https://***/xingyi-li/SymmNeRF. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Object Detection Under Varying Illuminances Using the Fusion of Dual-Attention Mode and Far Infrared-Color image

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Guo, Jiaren Tao, Yanyun Huang, Zihao Xu, Biao School of Rail Transportation Soochow University Suzhou215005 China Key Laboratory of Information Processing and Intelligent Control Shanghai Jiaotong University 350121 China Fuzhou350121 China State Key Laboratory of New Software Nanjing University Nanjing350121 China

The multi-scale object detection under varying illuminances is a difficult task. To deal with it, we propose a dual-attention mechanism object detection model called Dual-AttentionNet. Owing to the difference between the thermal object and background in the far infrared (FIR) images, the saliency region attention extracted from FIR images can successfully cover the thermal objects. However, sometimes, the saliency region attention cannot entirely cover the small-scale objects that are not so salient. Consequently, the segmentation attention is explored to focus on the super pixels containing the thermal objects and remove the background. Therefore, some small-scale objects missed by saliency attention can be still covered by the segmentation attention. The segmentation attention and saliency attention together form the dual-attention mechanism of Dual-AttentionNet. Additionally, the fusion of infrared and color images (FIR-color) is adopted to increase the details and contour information of objects under low illuminance. Through the dual-attention mode performed on FIR-color image (FIR-color+Dual-attention mode), the multiscale objects can be enhanced and concentrated, and the general detector in Dual-AttentionNet can detect objects with small computational efforts. Ablation experiment is conducted, and the FIR-color+Dual-attention mode greatly improves the robustness of detection compared with FIR-color, FIR+Saliency attention and FIR+Segmentation attention modes. Compared with the typical multispectral pedestrian detection models, Dual-AttentionNet yields a higher mean average precision and a lower miss rate in object detection at day and night in most cases. Moreover, Dual-AttentionNet is comprehensively tested on different FIR-color image datasets and obtains high accuracy on these examples. This outcome illustrates the strong generalization performance of Dual-AttentionNet. © 2023, The Authors. All rights reserved.

关键词： image fusion

A Parallel Read-Write Circuit Design for Driving Memristor Crossbar Array

学校读者我要写书评

暂无评论

A Parallel Read-Write Circuit Design for Driving Memristor C...

Neuromorphic Computing (ICNC), International Conference on

作者： Ningye Jiang Mingxuan Jiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

Memristor crossbar array is considered as a promising circuit module for accelerating neural networks. Because the memristor is tunable and multi-state, it is important to design applicable Read-Write (RW) circuit for driving memristor crossbar array. In this paper, a novel RW circuit based on analog circuits is proposed for tuning memristors in high-dimensional array parallelly, which is scalable and low-overhead. The standalone RW circuit schematic is presented for reading/writing single memristor and verified in circuit simulation. Then, we extend and apply this circuit into a two-dimensional memristor crossbar array. The performance of memristor crossbar array controlled by designed RW circuits is verified via the simulations under various machine learning datasets. The comparison with related works is presented, which demonstrates the advantages of the proposed RW circuit regarding overhead and anti-error.

关键词：

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Att...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kuo Guo Yifan Li Hao Chen Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University and Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Computational Biology Department School of Computer Science Carnegie Mellon University Pittsburgh PA USA

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function.

关键词：

Distributed Resource Allocation via Accelerated Saddle Point Dynamics

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第9期8卷 1588-1599页

作者： Wen-Ting Lin Yan-Wu Wang Chaojie Li Xinghuo Yu School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 Key Laboratory of Image Processing and Intelligent Control Ministry of EducationHuazhong University of Science and TechnologyWuhan 430074China School of Electrical Engineering and Telecommunications University of New South WalesSydney NSW 2052Australia School of Engineering Royal Melbourne Institute of Technology(RMIT University)Melbourne VIC 3000Australia

In this paper,accelerated saddle point dynamics is proposed for distributed resource allocation over a multi-agent network,which enables a hyper-exponential convergence ***,an inertial fast-slow dynamical system with vanishing damping is introduced,based on which the distributed saddle point algorithm is *** dual variables are updated in two time scales,i.e.,the fast manifold and the slow *** the fast manifold,the consensus of the Lagrangian multipliers and the tracking of the constraints are pursued by the consensus *** the slow manifold,the updating of the Lagrangian multipliers is accelerated by inertial ***-exponential stability is defined to characterize a faster convergence of our proposed algorithm in comparison with conventional primal-dual algorithms for distributed resource *** simulation of the application in the energy dispatch problem verifies the result,which demonstrates the fast convergence of the proposed saddle point dynamics.

关键词： Accelerated saddle point dynamic distributed resource allocation hyper-exponential stability power dispatch