检索结果-内蒙古大学图书馆

Learning Inverse Laplacian Pyramid for Progressive Depth Completion

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Kun Yan, Zhiqiang Fan, Junkai Li, Jun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Depth completion endeavors to reconstruct a dense depth map from sparse depth measurements, leveraging the information provided by a corresponding color image. Existing approaches mostly hinge on single-scale propagation strategies that iteratively ameliorate initial coarse depth estimates through pixel-level message passing. Despite their commendable outcomes, these techniques are frequently hampered by computational inefficiencies and a limited grasp of scene context. To circumvent these challenges, we introduce LP-Net, an innovative framework that implements a multi-scale, progressive prediction paradigm based on Laplacian Pyramid decomposition. Diverging from propagation-based approaches, LP-Net initiates with a rudimentary, low-resolution depth prediction to encapsulate the global scene context, subsequently refining this through successive upsampling and the reinstatement of high-frequency details at incremental scales. We have developed two novel modules to bolster this strategy: 1) the Multi-path Feature Pyramid module, which segregates feature maps into discrete pathways, employing multi-scale transformations to amalgamate comprehensive spatial information, and 2) the Selective Depth Filtering module, which dynamically learns to apply both smoothness and sharpness filters to judiciously mitigate noise while accentuating intricate details. By integrating these advancements, LP-Net not only secures state-of-the-art (SOTA) performance across both outdoor and indoor benchmarks such as KITTI, NYUv2, and TOFDC, but also demonstrates superior computational efficiency. At the time of submission, LP-Net ranks 1st among all peer-reviewed methods on the official KITTI leaderboard. The source code will be made publicly accessible upon paper acceptance. © 2025, CC BY-NC-SA.

关键词： Laplace transforms

Garment Animation NeRF with Color Editing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Renke Zhang, Meng Li, Jun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Generating high-fidelity garment animations through traditional workflows, from modeling to rendering, is both tedious and expensive. These workflows often require repetitive steps in response to updates in character motion, rendering viewpoint changes, or appearance edits. Although recent neural rendering offers an efficient solution for computationally intensive processes, it struggles with rendering complex garment animations containing fine wrinkle details and realistic garment-and-body occlusions, while maintaining structural consistency across frames and dense view rendering. In this paper, we propose a novel approach to directly synthesize garment animations from body motion sequences without the need for an explicit garment proxy. Our approach infers garment dynamic features from body motion, providing a preliminary overview of garment structure. Simultaneously, we capture detailed features from synthesized reference images of the garment's front and back, generated by a pre-trained image model. These features are then used to construct a neural radiance field that renders the garment animation video. Additionally, our technique enables garment recoloring by decomposing its visual elements. We demonstrate the generalizability of our method across unseen body motions and camera views, ensuring detailed structural consistency. Furthermore, we showcase its applicability to color editing on both real and synthetic garment data. Compared to existing neural rendering techniques, our method exhibits qualitative and quantitative improvements in garment dynamics and wrinkle detail modeling. Code is available at https://***/wrk226/GarmentAnimationNeRF. Copyright © 2024, The Authors. All rights reserved.

关键词： Animation

Knowledge Transfer Evolutionary Search with Hybrid Evaluation Criteria for Lightweight Neural Architectures

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Qian, Xiaoxue Liu, Fang Jiao, Licheng Zhang, Xiangrong Huang, Xinyan Li, Shuo Chen, Puhua Liu, Xu School of Artificial Intelligence Xidian University Xi’an710071 China Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation

Relying on the availability of massive labeled samples, most neural architecture search (NAS) methods focus on searching large and complex structures, while few approaches automatically design lightweight networks for label-limited tasks. To this end, we propose a knowledge transfer evolutionary search with hybrid evaluation criteria for lightweight neural architectures. We develop task-driven search space, search strategy, training strategy, and evaluation criteria for the evolutionary NAS, and verify it with synthetic aperture radar (SAR) images. SAR image classification is a typical label-limited task due to the specific imaging mechanism of SAR. Specifically, we build a SAR-tailored search space with an appropriate scale for reducing the algorithm complexity;and design topology pruning-based mutation operators to search lightweight architectures. Meanwhile, a knowledge transfer training strategy and hybrid evaluation criteria are explored to ensure the NAS quickly and robustly. Experimental results show that the proposed method can search for superior neural architectures, thus improving the classification performance of SAR images. © 2022, The Authors. All rights reserved.

关键词： Synthetic aperture radar

An R-SIFT image Matching intelligent Algorithm Applied to Hardware Trojan Detection

学校读者我要写书评

暂无评论

An R-SIFT Image Matching Intelligent Algorithm Applied to Ha...

2021 International Conference on Cloud Computer, IoT and Intelligence System, CCIIS 2021

作者： Sun, Chen Liang, Pujiang Li, Lingling Ma, Jingjing Jiao, Licheng Liu, Fang Science and Technology on Reliability Physics and Application of Electronic Component Laboratory Guangzhou511370 China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education International Research Center for Intelligent Perception and Computation Joint International Research Laboratory of Intelligent Perception and Computation School of Artificial Intelligence Xidian University Xi'an710071 China

Malicious modification, deletion or addition of some modules in the integrated circuits (ICs) will cause the chip to be attacked, which is called Hardware Trojans (HTs). Reverse engineering (RE) is a classic destructive method and widely used in HTs detection. However, RE is very time-consuming and error prone. In this paper, based on RE, we propose the R-SIFT algorithm to match image and reformulate the Trojan detection problem as change detection problem. For the R-SIFT algorithm, the ratio of exponentially weighted averages (Roewa) operator is introduced into the scale-invariant feature transform (SIFT) algorithm. Experiments show that the proposed method has 7 to 56 times more matching points than the original SIFT can be effectively applied to HTs detection. © Published under licence by IOP Publishing Ltd.

关键词： Reverse engineering

Customized Generation Reimagined: Fidelity and Editability Harmonized

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jin, Jian Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent trade-off between concept fidelity and editability, i.e., between precisely modeling the concept and faithfully adhering to the prompts. Previous methods reluctantly seek a compromise and struggle to achieve both high concept fidelity and ideal prompt alignment simultaneously. In this paper, we propose a "Divide, Conquer, then Integrate" (DCI) framework, which performs a surgical adjustment in the early stage of denoising to liberate the fine-tuned model from the fidelity-editability trade-off at inference. The two conflicting components in the trade-off are decoupled and individually conquered by two collaborative branches, which are then selectively integrated to preserve high concept fidelity while achieving faithful prompt adherence. To obtain a better fine-tuned model, we introduce an image-specific Context Optimization (ICO) strategy for model customization. ICO replaces manual prompt templates with learnable image-specific contexts, providing an adaptive and precise fine-tuning direction to promote the overall performance. Extensive experiments demonstrate the effectiveness of our method in reconciling the fidelity-editability trade-off. Code is available at https://***/jinjianRick/DCI_ICO. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

Traffic Pattern Sharing for Federated Traffic Flow Prediction with Personalization

学校读者我要写书评

暂无评论

Traffic Pattern Sharing for Federated Traffic Flow Predictio...

IEEE International Conference on Data Mining (ICDM)

作者： Hang Zhou Wentao Yu Sheng Wan Yongxin Tong Tianlong Gu Chen Gong School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China SKLSDE Beihang University China Engineering Research Center of Trustworthy AI (Ministry of Education) Jinan University China

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

Accurate Traffic Flow Prediction (TFP) is crucial for enhancing the efficiency and safety of transportation systems, so it has attracted intensive researches by exploiting spatial-temporal dependencies within road networks. However, existing works only consider the case of centralized data collection with all traffic data observed, which may raise privacy concerns as each region of a city may have its own traffic administration department and the traffic data is not allowed to distribute. Therefore, this paper proposes to use Federated Learning (FL) to address this issue by allowing all clients (i.e., traffic administration departments in all regions in our problem) to collaboratively train TFP models without exchanging raw data, thereby offering a solution in maintaining data privacy. Nevertheless, most existing FL methods aim to learn a global model that performs well universally, so they cannot well handle the non-Independent and Identically Distributed (non-IID) traffic data naturally over different regions. To cope with this problem, this paper develops a new FL framework termed “personalized Federated learning with Traffic Pattern Sharing” (FedTPS) to solve federated TFP problem. Our FedTPS critically exploits the underlying common traffic patterns (e.g., morning and evening rush hours) shared across different city regions and meanwhile maintaining the region-specific data characteristics in a personalized FL manner. Specifically, to extract the common traffic patterns, we decompose the traffic data in each client via using discrete wavelet transform, where the low-frequency components uncover the stable traffic dynamics of different regions and thus can be considered as the common traffic patterns. These common patterns are then shared among different clients through traffic pattern repositories on the server side to aid the global collaborative traffic flow modeling. Moreover, the model components capturing spatial-temporal dependencies in traffic data are r

关键词： Training Data privacy Federated learning Urban areas Transportation Transforms Traffic control Data models Safety Servers

LATEXBLEND: Scaling Multi-concept Customized Generation with Latent Textual Blending

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jin, Jian Yu, Zhenbo Shen, Yang Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Sci. & Tech. China

Customized text-to-image generation renders user-specified concepts into novel contexts based on textual prompts. Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency. In this paper, we propose LATEXBLEND, a novel framework for effectively and efficiently scaling multi-concept customized generation. The core idea of LATEXBLEND is to represent single concepts and blend multiple concepts within a Latent Textual space, which is positioned after the text encoder and a linear projection. LATEXBLEND customizes each concept individually, storing them in a concept bank with a compact representation of latent textual features that captures sufficient concept information to ensure high fidelity. At inference, concepts from the bank can be freely and seamlessly combined in the latent textual space, offering two key merits for multi-concept generation: 1) excellent scalability, and 2) significant reduction of denoising deviation, preserving coherent layouts. Extensive experiments demonstrate that LATEXBLEND can flexibly integrate multiple customized concepts with harmonious structures and high subject fidelity, substantially outperforming baselines in both generation quality and computational efficiency. Project Page. Copyright © 2025, The Authors. All rights reserved.

关键词：

Aligning Multiple Knowledge Graphs in a Single Pass

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Yaming Wang, Zhe Guan, Ziyu Zhao, Wei Lu, Weigang Huang, Xinyan Cui, Jiangtao He, Xiaofei State Key Laboratory of Integrated Services Networks School of Computer Science and Technology Xidian University Xi’an China Key Laboratory of Intelligent Perception and Image UnDerstanding The Ministry of Education The School of Artificial Intelligence Xidian University Xi’an China State Key Laboratory of CAD&CG Zhejiang University Hangzhou China

Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of our knowledge, no existing EA method considers aligning multiple (more than two) KGs. To fill this research gap, in this work, we study a novel problem of aligning multiple KGs and propose an effective framework named MultiEA to solve the problem. First, we embed the entities of all the candidate KGs into a common feature space by a shared KG encoder. Then, we explore three alignment strategies to minimize the distances among pre-aligned entities. In particular, we propose an innovative inference enhancement technique to improve the alignment performance by incorporating high-order similarities. Finally, to verify the effectiveness of MultiEA, we construct two new real-world benchmark datasets and conduct extensive experiments on them. The results show that our MultiEA can effectively and efficiently align multiple KGs in a single pass. We release the source codes of MultiEA at: https://***/kepsail/MultiEA. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

Adaptive Pedestrian Trajectory Prediction via Target-Directed Angle Augmentation

学校读者我要写书评

暂无评论

Adaptive Pedestrian Trajectory Prediction via Target-Directe...

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hao Kong Jie Xu Shenjian Gong Jian Yang Shanshan Zhang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Pedestrian trajectory prediction is an important task for many applications such as autonomous driving and surveillance systems. Yet the prediction performance drops dramatically when applying a model trained on the source domain to a new target domain. Therefore, it is of great importance to adapt a predictor to a new domain. Previous works mainly focus on feature-level alignment to solve this problem. In contrast, we solve it from a new perspective of instance-level alignment. Specifically, we first point out one key factor of the domain gaps, i.e., trajectory angles, and then augment the source training data by target-directed orientation augmentation so that its distribution matches with that of the target data. In this way, the trajectory predictor trained on the aligned source data performs better on the target domain. Experiments on standard baselines show that our method improves the state of the art by a large margin. The source code is available at https://***/NeoKH/PTP-DA.

关键词：