Model Selection for Surface Approximation and Scene Interpretation
表面近似和场景解释的模型选择
基本信息
- 批准号:265030540
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:德国
- 项目类别:Research Grants
- 财政年份:2014
- 资助国家:德国
- 起止时间:2013-12-31 至 2018-12-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Structure from Motion (SfM) and Multi-View Stereo (MVS) methods provide affordable means for 3D reconstruction. However, the generated output, typically point clouds, are subject to errors, missing regions, and, quite often, severe outliers. The point cloud is also a rather crude form of data in the sense that no higher level geometric or semantic information is immediately accessible.In the context of building facades, this project seeks to develop methods that derive more versatile models from a MVS point cloud. We base our approach on the insight that a combination of geometric and semantic regularization is key to a plausible abstraction of the input data. We propose to alternate between geometric regularization and semantic interpretation with both sides providing information to each other. In the resulting iterative scheme, the geometric side can make use of semantic information in order to apply specific priors on the reconstruction. The semantic interpretation side, on the other hand, benefits from the exchange by means of the improved and idealized geometric abstraction in addition to the initial visual data.The output of the proposed method will be an abstraction of the input data. Noise, outliers, and "unimportant" details are culled away to retain the essence of the building facade. The individual parts of the generated model will have a semantic meaning, in the form of labels such as "window", "balcony", and "door". In addition, the architectural style as well as the structure of the facade (e.g., the pattern of window repetitions) will be known.We believe that these methods are an important step towards rapid and affordable generation of detailed city models where the reconstruction is not only visually accurate, but also semantically enriched.In the first year of the first funding period, we conducted initial testing and developed the basic framework, the design of which was strongly guided by experiments. Despite the short duration of the project so far, we demonstrate convincing results on challenging input data and argue that further development is indeed warranted. In the second funding period, we will concentrate our efforts on improved geometric regularization and semantic interpretation as well as a proper, quantitative evaluation. In addition, we will improve our data acquisition and texturing capabilities to increase the visual fidelity of the idealized abstraction. As an additional application scenario of the idealized, visually accurate semantically labeled abstraction, we will compare reconstructions and automatically detect changes on building facades that will be classified based on our semantically enriched data.
运动恢复结构(SfM)和多视图立体(MVS)方法为3D重建提供了经济实惠的手段。然而,生成的输出(通常是点云)会出现错误、缺失区域,并且通常会出现严重的离群值。点云也是一种相当粗糙的数据形式,因为无法立即访问更高级别的几何或语义信息。在建筑立面的背景下,该项目寻求开发从MVS点云派生更通用模型的方法。我们基于我们的方法的洞察力,几何和语义正则化的组合是一个合理的抽象的输入数据的关键。我们建议在几何正则化和语义解释之间交替进行,双方相互提供信息。在得到的迭代方案中,几何侧可以利用语义信息,以便在重建上应用特定的先验。另一方面,语义解释方面受益于除了初始视觉数据之外的改进的和理想化的几何抽象的交换。所提出的方法的输出将是输入数据的抽象。噪音、异常值和“不重要”的细节被剔除,以保留建筑立面的本质。生成的模型的各个部分将具有语义含义,以标签的形式,如“窗户”,“阳台”和“门”。此外,建筑风格以及立面的结构(例如,我们相信这些方法是快速和负担得起的生成详细城市模型的重要一步,重建不仅在视觉上准确,而且在语义上丰富。在第一个资助期的第一年,我们进行了初步测试,并开发了基本框架,其设计在很大程度上受到实验的指导。尽管到目前为止,该项目的持续时间很短,但我们在具有挑战性的输入数据上展示了令人信服的结果,并认为确实有必要进一步开发。在第二个资助期,我们将集中精力改进几何正则化和语义解释,以及适当的定量评估。此外,我们将改进我们的数据采集和纹理功能,以增加理想化抽象的视觉保真度。作为理想化的、视觉上准确的语义标记抽象的附加应用场景,我们将比较重建并自动检测建筑立面上的变化,这些变化将根据我们语义丰富的数据进行分类。
项目成果
期刊论文数量(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Automatic Building Abstraction from Aerial Photogrammetry
- DOI:10.5194/isprs-annals-iv-2-w4-243-2017
- 发表时间:2017-09
- 期刊:
- 影响因子:0
- 作者:A. Ley;R. Hänsch;O. Hellwich
- 通讯作者:A. Ley;R. Hänsch;O. Hellwich
SyB3R: A Realistic Synthetic Benchmark for 3D Reconstruction from Images
SyB3R:图像 3D 重建的现实综合基准
- DOI:10.1007/978-3-319-46478-7_15
- 发表时间:2016
- 期刊:
- 影响因子:0
- 作者:A. Ley;R. Hänsch;O. Hellwich
- 通讯作者:O. Hellwich
HIGH QUALITY FACADE SEGMENTATION BASED ON STRUCTURED RANDOM FOREST, REGION PROPOSAL NETWORK AND RECTANGULAR FITTING
- DOI:10.5194/isprs-annals-iv-2-223-2018
- 发表时间:2018-05
- 期刊:
- 影响因子:0
- 作者:Kujtim Rahmani;H. Mayer
- 通讯作者:Kujtim Rahmani;H. Mayer
RECONSTRUCTING WHITE WALLS: MULTI-VIEW, MULTI-SHOT 3D RECONSTRUCTION OF TEXTURELESS SURFACES
重建白墙:无纹理表面的多视图、多镜头 3D 重建
- DOI:10.5194/isprs-annals-iii-3-91-2016
- 发表时间:2016
- 期刊:
- 影响因子:0
- 作者:A. Ley;R. Hänsch;O. Hellwich
- 通讯作者:O. Hellwich
Depth Map Based Facade Abstraction from Noisy Multi-View Stereo Point Clouds
从嘈杂的多视图立体点云中基于深度图的立面抽象
- DOI:10.1007/978-3-319-45886-1_13
- 发表时间:2016
- 期刊:
- 影响因子:0
- 作者:A. Ley;O. Hellwich
- 通讯作者:O. Hellwich
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Professor Dr.-Ing. Olaf Hellwich其他文献
Professor Dr.-Ing. Olaf Hellwich的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Professor Dr.-Ing. Olaf Hellwich', 18)}}的其他基金
Kombinierte Objektdetektion und physikalische Modell-Inversion für PolINSAR-Bilddaten
PolINSAR 图像的目标检测和物理模型反演相结合
- 批准号:
190378420 - 财政年份:2011
- 资助金额:
-- - 项目类别:
Research Grants
Constraint on Tien Shan structure and dynamics from integrative modelling of new satellite gravity-, GNSS-, SAR- and seismic data
新卫星重力、GNSS、SAR和地震数据综合建模对天山结构和动力学的约束
- 批准号:
111515381 - 财政年份:2009
- 资助金额:
-- - 项目类别:
Priority Programmes
Objektkategorisierung für polarimetrisch-interferometrische SAR-Daten
偏振干涉 SAR 数据的对象分类
- 批准号:
22114955 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Research Grants
Automatic 3D-reconstruction of buildings using highly resolving video sequences
使用高分辨率视频序列自动 3D 重建建筑物
- 批准号:
62030896 - 财政年份:2007
- 资助金额:
-- - 项目类别:
Research Grants
Automatic 3D-reconstruction of buildings using highly resolving video sequences
使用高分辨率视频序列自动 3D 重建建筑物
- 批准号:
5456384 - 财政年份:2005
- 资助金额:
-- - 项目类别:
Research Grants
相似国自然基金
Intelligent Patent Analysis for Optimized Technology Stack Selection:Blockchain BusinessRegistry Case Demonstration
- 批准号:
- 批准年份:2024
- 资助金额:万元
- 项目类别:外国学者研究基金项目
连锁群选育法(Linkage Group Selection)在柔嫩艾美耳球虫表型相关基因研究中应用
- 批准号:30700601
- 批准年份:2007
- 资助金额:17.0 万元
- 项目类别:青年科学基金项目
相似海外基金
Evolutionarily smart vaccine strain selection for proactive vaccinology
用于主动疫苗学的进化智能疫苗株选择
- 批准号:
MR/Y004337/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
mRNA selection for translation: beyond the canonical view
用于翻译的 mRNA 选择:超越规范观点
- 批准号:
BB/Y005783/1 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Research Grant
Development of Integrated Quantum Inspired Algorithms for Shapley Value based Fast and Interpretable Feature Subset Selection
基于 Shapley 值的快速且可解释的特征子集选择的集成量子启发算法的开发
- 批准号:
24K15089 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (C)
Leveraging Machine Learning to Examine Engineering Students Self-selection in Entrepreneurship Education Programs
利用机器学习检查工科学生在创业教育项目中的自我选择
- 批准号:
2321175 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
ERI: Intelligent Modeling and Parameter Selection in Distributed Optimization for Power Networks
ERI:电力网络分布式优化中的智能建模和参数选择
- 批准号:
2347120 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Standard Grant
Indication selection, patient stratification, and IND preparation for STX-002: the first-in-class LRG1 inhibitor for treatment of chronic kidney disease and immunotherapy-resistant tumours.
STX-002的适应症选择、患者分层和IND准备:用于治疗慢性肾病和免疫治疗耐药肿瘤的一流LRG1抑制剂。
- 批准号:
10092585 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Collaborative R&D
Universal Model Selection Criteria for Scientific Machine Learning
科学机器学习的通用模型选择标准
- 批准号:
DE240100144 - 财政年份:2024
- 资助金额:
-- - 项目类别:
Discovery Early Career Researcher Award
AI tools for biocatalyst route selection
用于生物催化剂路线选择的人工智能工具
- 批准号:
10076156 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Grant for R&D
Development of a food bolus formation ability evaluation system to support the selection of appropriate food forms.
开发食物团形成能力评估系统以支持选择合适的食物形式。
- 批准号:
23K09279 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (C)
A novel neural pathway of preferential food selection for high carbohydrate and fat diets.
高碳水化合物和脂肪饮食的优先食物选择的新神经通路。
- 批准号:
23H02965 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Scientific Research (B)