检索结果-内蒙古大学图书馆

41st Computer Graphics International Conference, CGI 2024

作者： Liu, Yangyue Hu, Yong shen, xukun State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China School of New Media Art and Design Beihang University Beijing100191 China

ISBN: (纸本)9783031820205

Currently, monocular 3D face capture and tracking methods are difficult to ensure the accuracy of identity and expression, and speech-driven 3D facial animation methods are challenging to acquire head pose and upper facial expression. In response, we propose a video- and speech-driven 3D facial animation synthesis method that attempts to combine the benefits of these methods and avoid their weaknesses. Specifically, to facilitate animation and handle the problem of character identity accuracy, we generate character appearance templates by registering a 3D morphable model (3DMM) to a rigid model. To address the limitations of different methods for acquiring expressions and poses, we design an expression fusion network based on the 3DMM space to fuse the expression data acquired by different modalities and output unified facial expression data. Finally, due to the limitation of the dataset ignoring the eye movements, we design an eye movement enhancement network to add eyelid movements by modifying the facial expression data and then replacing the eye region to get the final 3D face mesh animation. Through detailed experiments, we demonstrate that our method can generate speech-visual synchronized 3D face animations while obtaining better performance results than the current concerns of using monocular video images or speech-driven generation of 3D face animation methods independently. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

JGHand: Joint-Driven Animatable Hand Avater via 3D Gaussian Splatting

arXiv

引用

arXiv 2025年

作者： Sun, Zhoutao shen, xukun Hu, Yong Zhong, Yuyou Zhou, Xueyang State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Since hands are the primary interface in daily interactions, modeling high-quality digital human hands and rendering realistic images is a critical research problem. Furthermore, considering the requirements of interactive and rendering applications, it is essential to achieve real-time rendering and driveability of the digital model without compromising rendering quality. Thus, we propose Jointly 3D Gaussian Hand (JGHand), a novel joint-driven 3D Gaussian Splatting (3DGS)-based hand representation that renders high-fidelity hand images in real-time for various poses and characters. Distinct from existing articulated neural rendering techniques, we introduce a differentiable process for spatial transformations based on 3D key points. This process supports deformations from the canonical template to a mesh with arbitrary bone lengths and poses. Additionally, we propose a real-time shadow simulation method based on per-pixel depth to simulate self-occlusion shadows caused by finger movements. Finally, we embed the hand prior and propose an animatable 3DGS representation of the hand driven solely by 3D key points. We validate the effectiveness of each component of our approach through comprehensive ablation studies. Experimental results on public datasets demonstrate that JGHand achieves real-time rendering speeds with enhanced quality, surpassing state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Text-driven 3D Human Generation via Contrastive Preference Optimization

arXiv

引用

arXiv 2025年

作者： Zhou, Pengfei shen, xukun Hu, Yong State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China

Recent advancements in Score Distillation Sampling (SDS) have significantly improved text-driven 3D human generation, enabling plausible synthesis from natural language descriptions. However, existing methods struggle with fine-grained semantic alignment, leading to inconsistencies in structure, texture, and attribute representation. To address these challenges, we propose a contrastive preference modeling framework that integrates both positive and negative prompts to enhance SDS. This approach refines text-conditioned generation, improving semantic consistency and 3D fidelity. Specifically, we introduce a preference optimization module that aggregates knowledge from multiple preference models to ensure accurate representation of intricate attributes and nuanced details. Additionally, we propose a negation preference module with static-dynamic negation prompts to systematically distinguish relevant details from extraneous elements, ensuring geometric and textural consistency. To further mitigate artifacts and prevent reward hacking, we develop an LLM-driven dynamic negation prompting mechanism that analyzes textual inputs, decomposes complex attributes, and filters irrelevant components. Extensive experiments demonstrate that our method achieves state-of-the-art performance, significantly enhancing texture realism, structure coherence, and overall visual alignment, particularly for complex and lengthy textual descriptions. © 2025, CC BY.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Guided Diffusion for Quantity-Controlled Remote Sensing Object Generation

引用

IEEE Geoscience and Remote Sensing Letters 2025年 22卷

作者： Yu, Zhiping Liu, Chenyang Zhong, Chuyu Zou, Zhengxia Shi, Zhenwei Beihang University School of Astronautics Department of Aerospace Intelligent Science and Technology Beijing100191 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Beihang University Shen Yuan Honors College Beijing100191 China

Accurate object counts represent essential semantical information in remote sensing imagery, significantly impacting applications such as traffic monitoring and urban planning. Despite the recent advances in text-to-image (T2I) generation in remote sensing, existing methods still face challenges in precisely controlling the number of object instances in generated images. To address this challenge, we propose a novel method, multi-grained guided diffusion (MGDiff). During training, unlike previous methods that relied solely on latent-space noise constraints, MGDiff imposes constraints at three distinct granularities: latent pixel, global counting, and spatial distribution. The multi-grained guidance mechanism matches the quantity prompts with object spatial layouts in the feature space, enabling our model to achieve precise control over object quantities. To benchmark this new task, we present Levir-QCG, a dataset comprising 10504 remote sensing images across five object categories, annotated with precise object counts and segmentation masks. We conducted extensive experiments to benchmark our method against previous methods on the Levir-QCG dataset. Compared to previous models, the MGDiff achieves an approximately +40% improvement in counting accuracy while maintaining higher visual fidelity and strong zero-shot generalization. To the best of our knowledge, this is the first work to research accurate object quantity control in remote sensing T2I generation. © 2004-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

arXiv

引用

arXiv 2025年

作者： Liu, Chenyang Chen, keyan Zhao, Rui Zou, Zhengxia Shi, Zhenwei The Department of Aerospace Intelligent Science and Technology School of Astronautics The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shen Yuan Honors College of Beihang University Beijing100191 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Recently, generative foundation models have significantly advanced large-scale text-driven natural image generation and have become a prominent research trend across various vertical domains. However, in the remote sensing field, there is still a lack of research on large-scale text-to-image (text2image) generation technology. Existing remote sensing image-text datasets are small in scale and confined to specific geographic areas and scene types. Besides, existing text2image methods have struggled to achieve global-scale, multi-resolution controllable, and unbounded image generation. To address these challenges, this paper presents two key contributions: the Git-10M dataset and the Text2Earth foundation model. Git-10M is a global-scale image-text dataset comprising 10.5 million image-text pairs, 5 times larger than the previous largest one. The dataset contains essential resolution information and covers a wide range of geographic scenes and contains essential geospatial metadata, significantly surpassing existing datasets in both size and diversity. Building on Git-10M, we propose Text2Earth, a 1.3 billion parameter generative foundation model based on the diffusion framework to model global-scale remote sensing scenes. Text2Earth integrates a resolution guidance mechanism, enabling users to specify image resolutions. A dynamic condition adaptation strategy is proposed for training and inference to improve image generation quality. Text2Earth not only excels in zero-shot text2image generation but also demonstrates robust generalization and flexibility across multiple tasks, including unbounded scene construction, image editing, and cross-modal image generation. This robust capability surpasses previous models restricted to the basic fixed size and limited scene types. On the previous text2image benchmark dataset, Text2Earth outperfoms previous models with a significant improvement of +26.23 FID and +20.95% Zero-shot Cls-OA metric. Our project page is https://chen-y

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Image Tagging by Semantic Neighbor Learning Using User-Contributed Social Image Datasets

引用

Tsinghua Science and technology 2017年第6期22卷 551-563页

作者： Feng Tian xukun shen Xianmei Liu Maojun Cao the School of Computer and Information Technology Northeast Petroleum University Daqing 163318 China Xukun Shen is with State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing 100191 China.

The explosive increase in the number of images on the Internet has brought with it the great challenge of how to effectively index, retrieve, and organize these resources. Assigning proper tags to the visual content is key to the success of many applications such as image retrieval and content mining. Although recent years have witnessed many advances in image tagging, these methods have limitations when applied to high-quality and large-scale training data that are expensive to obtain. In this paper, we propose a novel semantic neighbor learning method based on user-contributed social image datasets that can be acquired from the Web＇s inexhaustible social image content. In contrast to existing image tagging approaches that rely on high-quality image-tag supervision, we acquire weak supervision of our neighbor learning method by progressive neighborhood retrieval from noisy and diverse user-contributed image collections. The retrieved neighbor images are not only visually alike and partially correlated but also semantically related. We offer a step-by-step and easy-to-use implementation for the proposed method. Extensive experimentation on several datasets demonstrates that the performance of the proposed method significantly outperforms others.

关键词： image tag social image tagging user-contributed datasets semantic neighbor learning

来源：评论

学校读者我要写书评

暂无评论

Localizing object parts in 3D from a single image

引用

Science China(Information Sciences) 2019年第7期62卷 217-219页

作者： shen YIN Bin ZHOU Mingjia YANG Yu ZHANG State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang University

Object localization in 3D from 2D images is an important computer vision problem that enables modern robotic vision systems to interact properly with the objects present in the real world. Owing to its significance, techniques for recovering the 6-DOF pose and dimensions of objects from images has received increasing attention in recent years [1–3]. However, to the best of our knowledge,the existing approaches all focus on object-level inference instead of analyzing object parts. Most of

关键词： pro Localizing object parts in 3D from a single image

来源：评论

学校读者我要写书评

暂无评论

Learning Semantic Concepts from Noisy Media Collection for Automatic Image Annotation

引用

Chinese Journal of Electronics 2015年第4期24卷 790-794页

作者： TIAN Feng shen xukun School of Computer and Information Technology Northeast Petroleum University State Key Laboratory of Virtual Reality Technology and Systems Beihang University

Along with the explosive growth of images, automatic image annotation has attracted great interest of various research communities. However, despite the great progress achieved in the past two decades, automatic annotation is still an important open problem in computer vision, and can hardly achieve satisfactory performance in real-world environment. In this paper, we address the problem of annotation when noise is interfering with the dataset. A semantic neighborhood learning model on noisy media collection is proposed. Missing labels are replenished, and semantic balanced neighborhood is construct. The model allows the integration of multiple label metric learning and local nonnegative sparse *** construct semantic consistent neighborhood for each sample, thus corresponding neighbors have higher global similarity, partial correlation, conceptual similarity along with semantic balance. Meanwhile, an iterative denoising method is also proposed. The method proposed makes a marked improvement as compared to the current state-ofthe-art.

关键词： Image annotation Noisy media collection Semantic neighborhood

来源：评论

学校读者我要写书评

暂无评论

Unmanned aerial systems coordinate target allocation based on wolf behaviors

引用

Science China(Information Sciences) 2019年第1期62卷 205-207页

作者： Haibin DUAN Qing YANG Yimin DENG Pei LI Huaxin QIU Tianjie ZHANG Daifeng ZHANG Mengzhen HUO Yankai shen Bio-inspired Autonomous Flight Systems (BAFS) Research Group State Key Laboratory of Virtual Reality Technology and SystemsSchool of Automation Science and Electrical EngineeringBeihang University (BUAA)

Unmanned aerial systems (UASs), especially the cluster of UAS, are highly focused and widely used in various domains. The application of small and inexpensive UAS with a large-scale group to perform complex tasks has ... 详细信息

关键词： UAS Unmanned aerial systems coordinate target allocation based on wolf behaviors

来源：评论

学校读者我要写书评

暂无评论

A novel method based on color information for scanned data alignment 08

A novel method based on color information for scanned data a...

引用

VRST 2008 ACM Symposium on virtual reality Software and technology

作者： Yang, shen Qi, Yue Hou, Fei shen, xukun Zhao, Qinping State Key Laboratory of Virtual Reality Technology and Systems Beihang University China

ISBN: (纸本)9781595939517

This paper presents a rapid and robust method to align large sets of range scans captured by a 3D scanner automatically. The method incorporates the color information from the range data into the pairwise registration. Firstly, it detects the features using SIFT (Scale-Invariant Feature Transform) on grayscale images generated from two range scans to align. Then a quasi-dense matching algorithm, based on the match propagation principle, is applied to specify the matching pixel pairs between two images. All matches obtained are mapped to 3D space but in different world coordinates, and filtered by the 3D geometry constraint discovered from the range data. The remaining set of point correspondences is used to estimate the rigid transformation. Finally, a modified ICP (Iterative Closest Point) algorithm is applied to refine the result. The paper also describes a framework to use this alignment method for object reconstruction. The reconstruction proceeds by acquiring several range scans with color information from different directions, following which pair-wise of range data are aligned with the above method selectively and iteratively. Then a model graph containing the correct pair-wise matches is created and a span tree specifying a complete model is constructed. Finally a global optimization is performed to refine the result. This reconstruction technique achieves a robust and high performance in the application of rebuilding the 3D models of culture heritages for virtual museum automatically. Copyright 2008 ACM.

关键词： Global optimization

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：