检索结果-内蒙古大学图书馆

Joint self-supervised and reference-guided learning for depth inpainting

Computational Visual Media 2022年第4期8卷 597-612页

作者： Heng Wu Kui Fu Yifan Zhao Haokun Song Jia Li State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Depth information can benefit various computer vision tasks on both images and ***,depth maps may suffer from invalid values in many pixels,and also large *** improve such data,we propose a joint self-supervised and reference-guided learning approach for depth *** the self-supervised learning strategy,we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge *** module alternately learns a convolutional dictionary and sparse coding from a corrupted depth ***,both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map,which is effectively smoothed using local contextual *** reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth *** thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large *** summary,our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent *** results show that the proposed approach works well for both invalid value restoration and large hole inpainting.

关键词： depth inpainting self-supervised learning reference-guided learning

来源：评论

学校读者我要写书评

暂无评论

SADNet: Generating immersive virtual reality avatars by real-time monocular pose estimation

SADNet: Generating immersive virtual reality avatars by real...

引用

作者： Jiang, Ling Xiong, Yuan Wang, Qianqian Chen, Tong Wu, Wei Zhou, Zhong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Zhongguancun Laboratory Beijing China

Generating immersive virtual reality avatars is a challenging task in VR/AR applications, which maps physical human body poses to avatars in virtual scenes for an immersive user experience. However, most existing work is time-consuming and limited by datasets, which does not satisfy immersive and real-time requirements of VR systems. In this paper, we aim to generate 3D real-time virtual reality avatars based on a monocular camera to solve these problems. Specifically, we first design a self-attention distillation network (SADNet) for effective human pose estimation, which is guided by a pre-trained teacher. Secondly, we propose a lightweight pose mapping method for human avatars that utilizes the camera model to map 2D poses to 3D avatar keypoints, generating real-time human avatars with pose consistency. Finally, we integrate our framework into a VR system, displaying generated 3D pose-driven avatars on Helmet-Mounted Display devices for an immersive user experience. We evaluate SADNet on two publicly available datasets. Experimental results show that SADNet achieves a state-of-the-art trade-off between speed and accuracy. In addition, we conducted a user experience study on the performance and immersion of virtual reality avatars. Results show that pose-driven 3D human avatars generated by our method are smooth and attractive. © 2024 John Wiley & Sons Ltd.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A multi-strategy pigeon-inspired optimization approach to active disturbance rejection control parameters tuning for vertical take-off and landing fixed-wing UAV

引用

Chinese Journal of Aeronautics 2022年第1期35卷 19-30,I0001页

作者： Hangxuan HE Haibin DUAN State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China Peng Cheng Laboratory Shenzhen 518000China

In this *** Disturbance Rejection Control(ADRC)is utilized in the pitch control of a vertical take-off and landing fixed-wing Unmanned Aerial Vehicle(UAV)to address the problem of height fluctuation during the transition from hover to level *** the difficulty of parameter tuning of ADRC as well as the requirement of accuracy and rapidity of the controller,a Multi-Strategy Pigeon-Inspired Optimization(MSPIO)algorithm is *** Swarm Optimization(PSO),Genetic Algorithm(GA),the basic Pigeon-Inspired Optimization(PIO),and an improved PIO algorithm CMPIO are *** addition,the optimized ADRC control system is compared with the pure Proportional-Integral-Derivative(PID)control system and the non-optimized ADRC control *** effectiveness of the designed control strategy for forward transition is verified and the faster convergence speed and better exploitation ability of the proposed MSPIO algorithm are confirmed by simulation results.

关键词： Active Disturbance Rejection Control(ADRC) Pigeon-inspired optimization algorithm Transition mode Unmanned Aerial Vehicle(UAV) Vertical take-off and landing

来源：评论

学校读者我要写书评

暂无评论

Further results on consensus for coupled swarm systems 18

Further results on consensus for coupled swarm systems

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Wang, Shaojie Xiao, Jin Hu, Xiaoguang Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China

ISBN: (纸本)9798350312201

The motion of the swarm system can be composed of the absolute motion of the swarm as a whole and the relative motion between nodes. Especially for nonlinear swarm systems, their absolute motion remains unknown. This paper considers a synchronization model for continuous-time swarm systems, which can be viewed as a generalized version of the consensus model for multi-agent systems, where node dynamics can be linear or nonlinear, and the coupling function of the state between nodes can also be linear or nonlinear. This paper is dedicated to answer what the specific form of the synchronization function (i.e., the absolute motion of the synchronized swarm system) is, and how to determine the contribution rate of the nodes in the network to the synchronization function. We leverage the state decomposition method to determine the synchronization function. Specifically, the paper illustrates the relationship between the synchronization function and the solution of the isolated node. © 2023 IEEE.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Research on Electrical System Modeling of Aerostat Based on Harmony-SE 18

Research on Electrical System Modeling of Aerostat Based on ...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Pan, Xiang Xiao, Jin Hu, Xiaoguang Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China

ISBN: (纸本)9798350312201

In order to solve the problems of low efficiency of traditional model-based methods in the design and modeling of the electrical system of aerostat. Aiming at the design and modeling problems of aerostat electrical system, which is a typical multidisciplinary complex system, this paper firstly proposes a design method based on functional flow, state flow and information flow on the basis of the Harmony-SE method. The information flow is regarded as the element connecting between states and functions, and the requirements, structure and behavior model of the electrical system of aerostat is constructed. Then we put forward the method of building a structural model around the information flow and mapping the structural model to the integration of FMU model. We realized the physical modeling and model integration of part of the electrical system of aerostat, and finally completed the design and modeling of four parts of the electrical system of aerostat from requirements, functions, logic and physics. This method can improve the efficiency of multidisciplinary complex system design and modeling by optimizing the context use case repeated analysis and function design redundancy when the traditional model-based method is applied to multidisciplinary complex system design. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Text-prompt Camouflaged Instance Segmentation with Graduated Camouflage Learning 24

Text-prompt Camouflaged Instance Segmentation with Graduated...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Zhentao Xia, Changqun Qiao, Shengye Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Beijing China Pengcheng Laboratory Shenzhen China

ISBN: (纸本)9798400706868

Camouflaged instance segmentation (CIS) aims to detect and segment objects blending with their surroundings. While existing CIS methods rely heavily on fully-supervised training with massive precisely annotated data, consuming considerable annotation efforts yet struggling to segment highly camouflaged objects accurately. Despite their visual similarity to the background, camouflaged objects differ semantically. Since text associated with images offers explicit semantic cues to underscore this difference, we propose a novel approach: the first Text-Prompt based weakly-supervised camouflaged instance segmentation method named TPNet, leveraging semantic distinctions for effective segmentation. TPNet operates in two stages: pseudo mask generation and a self-training process. In the first stage, we align text prompts with images using a language-image model to obtain region proposals containing camouflaged instances. A Semantic-Spatial Iterative Fusion module is designed to assimilate spatial information with semantic insights, iteratively refining pseudo mask. In the second stage, Graduated Camouflage Learning, a self-training strategy, sequences training from simple to complex images based on camouflage levels, facilitating an effective learning gradient. Through the collaboration of the dual phases, our method offers a comprehensive experiment on two common benchmark and demonstrates a significant advancement, delivering a novel solution that bridges the gap between weak-supervised and high camouflaged instance segmentation. © 2024 Owner/Author.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Multi-domain Modeling and Optimization of Aircraft Electrical System Based on Modelica 18

The Multi-domain Modeling and Optimization of Aircraft Elect...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Xiao, Jin Li, Yue Hu, Xiaoguang Reality Technology and Systems Beihang University State Key Laboratory of Virtual Beijing China

ISBN: (纸本)9798350312201

Aircraft electrical system includes key equipment such as battery, step-down circuit, filter, motor and so on. It is a comprehensive system integrating machinery, electronics, control, thermodynamics and other fields. However, many current modeling and simulation methods are aimed at specific problems in a single domain or subsystem, and it is difficult to consider the coupling relationship between different domains. To solve the above problems, this paper uses the multi-domain physical system modeling language Modelica to establish the aircraft electrical system model library on the simulation platform Mworks, and simulates the electrical characteristics of each model, some parameters are optimized. The results show that the multi-domain modeling of aircraft electrical system based on Modelica language can realize the simulation results close to the actual, and the optimization of related parameters can effectively improve the system performance and improve the design efficiency. © 2023 IEEE.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

A Conditional Diffusion Model for 3D Human Pose Estimation 4

A Conditional Diffusion Model for 3D Human Pose Estimation

引用

4th International Conference on Consumer Electronics and Computer Engineering, ICCECE 2024

作者： Chen, Zhangmeng Dai, Ju Pan, Junjun Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9798350384062

Monocular 3D human pose estimation is a highly challenging task due to inherent depth ambiguity and occlusion. In response to these challenges, many previous works have utilized temporal information to enhance the richness of information. However, such methods can only derive a specific 3D pose from a single image, which fails to address ambiguity. Fortunately, denoising diffusion probabilistic models have recently achieved success in various computer vision tasks (e.g., generating images and image segmentation). Diffusion-based methods produce a set of possible result for each image. Inspired by this, we explore a novel Conditional Diffusion-based 3D human Pose estimation framework (CDiffPose) that formulates 3D human pose estimation as a 2D keypoints-guided 3D pose synthesis problem. We utilize a pre-trained model to represent 2D keypoints information as conditioning information. Subsequently, we inject the conditional information into the denoising model. Our denoising model (Denoiser) adopts a cascaded approach involving GCN and Transformers. Finally, the model generates multiple 3D candidates poses for a single 2D keypoint to alleviate the inherent depth ambiguity. Extensive experiments are conducted on Human3.6M benchmark, our proposed method demonstrates competitive performance. © 2024 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

D-scheduler:A scheduler in time-triggered distributed system through decoupling dependencies between tasks and messages

引用

Science China(Technological Sciences) 2024年第1期67卷 183-196页

作者： YANG TingTing ZHANG YuQi YUE FengLai WUNIRI QiQiGe TONG Chao School of Computer Science&Engineering Beihang UniversityBeijing 100191China State Key Laboratory of Virtual Reality Technology and Systems Beihang UniversityBeijing 100191China National Innovation Center of Intelligent and Connected Vehicles Beijing 100176China

Time-triggered architecture,as a mainstream design of the distributed real-time system,has been successfully applied in the aerospace,automotive and mechanical ***,time-triggered scheduling is a challenging NP-hard *** are few studies that could quickly solve the scheduling problem of large distributed time-triggered *** solve this problem,a communication affinity parameter is defined in this paper to describe the degree of bias of the shaper task towards sending or receiving *** on this,an innovative task-message decoupling model named D-scheduler is built to reduce the computation complexity of the scheduling problem in large-scale ***,we provide mathematical proof that our model is a convex optimization that is easy to solve with existing computational *** experiments substantiate the efficacy of the *** dramatically reduces the scheduling complexity of large-scale real-time systems with a small loss of solving space compared to the federal scheduler.

关键词： time-triggered architecture time-triggered scheduling communication affinity parameter task-message decoupling model

来源：评论

学校读者我要写书评

暂无评论

FreeGen: Bridging Visual-Linguistic Discrepancies Towards Diffusion-based Pixel-level Data Synthesis 39

FreeGen: Bridging Visual-Linguistic Discrepancies Towards Di...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Wenzhuang Ma, Mingcan Chen, Yong Xia, Changqun Liang, Zhenbao Li, Jia State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University China Geely Automobile Research Institute China Pengcheng Laboratory China

ISBN: (纸本)157735897X

Text-to-image diffusion model has inspired research into text-to-data synthesis without human intervention, where spatial attentions correlated with semantic entities in text prompts are primarily interpreted as pseudo-masks. However, these vannila attentions often deliver visual-linguistic discrepancies, in which the associations between image features and entity-level tokens are unstable and divergent, yielding inferior masks for realistic applications, especially in more practical open-vocabulary settings. To tackle this issue, we propose a novel text-guided self-driven generative paradigm, termed FreeGen, which addresses the discrepancies by recalibrating intrinsic visual-linguistic correlations and serves as a real-data-free method to automatically synthesize open-vocabulary pixel-level data for arbitrary entities. Specifically, we first learn an Attention Self-Rectification mechanism to reproject the inherent attention matrices to achieve robust semantic alignment, thereby obtaining class-discriminative masks. A Temporal Fluctuation Factor is present to assess mask quality based on its variation over uniform sampling timesteps, enabling the selection of reliable masks. These masks are then employed as self-supervised signals to support the learning of an Entity-level Grounding Decoder in a self-training manner, thus producing open-vocabulary segmentation results. Extensive experiments show that the existing segmenters trained on FreeGen narrow the performance gap with real data counterparts and remarkably outperform the state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

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：