CAREER: Modeling Uncertainties for Geometry Processing

职业：几何处理的不确定性建模

• 批准号: 2047677
• 负责人: Qixing Huang
• 金额: $ 50.46万
• 依托单位: University of Texas at Austin
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-04-01 至 2026-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2047677&HistoricalAwards=false
• 关键词: CAREER; Modeling; Uncertainties; Geometry; Processing

Advances in acquisition devices have enabled the generation of rich 3D data that captures physical objects/scenes at a full spectrum of scales ranging from molecules to urban environments. Coupled with such 3D information is impressive progress in geometry processing aiming to reconstruct, analyze, and model 3D geometries. As 3D sensors become more affordable and ubiquitous, applications of geometry processing algorithms are expanding from traditional domains such as computer-aided design and architecture to integrative modules of interactive and autonomous systems in the life sciences, self-driving cars, and national defense. For these new applications, the currently dominant approach where geometry processing algorithms generate a single output (e.g., one reconstructed mesh) is not sufficient, because essential information such as the accuracy of the output, other plausible solutions, and data uncertainty in data-driven approaches is not conveyed. Such information is indispensable for critical decision making, such as whether a 3D reconstruction is accurate enough for surgery planning or bridge damage inspection, and if not where to add additional inputs to improve the reconstruction quality. This project will establish a unified and transformative framework to model and quantify uncertainties of geometry processing algorithms, and will develop new algorithms that possess uncertainty outputs.This research will provide the first systematic study of uncertainty quantification for geometry processing. To this end, the project will establish an uncertainty quantification (UQ) framework that seamlessly integrates tools in probability theory, statistics, and deep generative models with core data representations and algorithms in geometry processing. Building upon a careful examination of the connection between the output and various uncertainty sources (input, algorithm, and data), the framework will incorporate a unified mixture model for encoding uncertainties via four thrusts, starting from algebraic approximations for modeling the local shape of a distribution to sampling and variational inference for characterizing mixture components. On the application side, the work will examine how uncertainties evolve in the geometry processing pipeline, starting from sensor uncertainty in scan registration and surface reconstruction to stochastic algorithms for structure detection to data uncertainty in data-driven geometry editing. On the algorithm side, the research will develop a unified framework that outputs mixture models to approximate the output distribution derived from different uncertainty sources. Evaluation of project outcomes will focus on three industrial disciplines: digital dental care, autonomous driving, and digital archaeology.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

采集设备的进步使得能够生成丰富的 3D 数据，这些数据可以捕捉从分子到城市环境等各种尺度的物理对象/场景。与此类 3D 信息相结合，旨在重建、分析和建模 3D 几何形状的几何处理取得了令人瞩目的进展。随着 3D 传感器变得更加便宜和普遍，几何处理算法的应用正在从计算机辅助设计和架构等传统领域扩展到生命科学、自动驾驶汽车和国防等交互式和自主系统的集成模块。对于这些新应用，当前占主导地位的几何处理算法生成单个输出（例如，一个重建的网格）的方法是不够的，因为没有传达诸如输出精度、其他合理解决方案以及数据驱动方法中的数据不确定性等基本信息。此类信息对于关键决策是不可或缺的，例如 3D 重建对于手术计划或桥梁损伤检查是否足够准确，如果不够准确，则应在何处添加额外输入以提高重建质量。该项目将建立一个统一的变革性框架来对几何处理算法的不确定性进行建模和量化，并将开发具有不确定性输出的新算法。本研究将为几何处理的不确定性量化提供首次系统研究。为此，该项目将建立一个不确定性量化（UQ）框架，将概率论、统计学和深度生成模型中的工具与几何处理中的核心数据表示和算法无缝集成。在仔细检查输出和各种不确定性源（输入、算法和数据）之间的联系的基础上，该框架将纳入一个统一的混合模型，通过四个推力对不确定性进行编码，从用于建模分布局部形状的代数近似到用于表征混合成分的采样和变分推理。在应用方面，这项工作将研究几何处理流程中的不确定性如何演变，从扫描配准和表面重建中的传感器不确定性到结构检测的随机算法，再到数据驱动的几何编辑中的数据不确定性。 在算法方面，该研究将开发一个统一的框架，输出混合模型来近似不同不确定性源得出的输出分布。项目成果的评估将重点关注三个行业学科：数字牙科护理、自动驾驶和数字考古学。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Scalable neural indoor scene rendering

• DOI: 10.1145/3528223.3530153
• 发表时间: 2022-07
• 期刊: ACM Transactions on Graphics (TOG)
• 作者: Xiuchao Wu;Jiamin Xu;Zihan Zhu;H. Bao;Qi-Xing Huang;J. Tompkin;Weiwei Xu

GeoLatent: A Geometric Approach to Latent Space Design for Deformable Shape Generators

• DOI: 10.1145/3618371
• 发表时间: 2023-12
• 期刊: ACM Transactions on Graphics (TOG)
• 作者: Haitao Yang;Bo Sun;Liyan Chen;Amy Pavel;Qixing Huang

Scalable image-based indoor scene rendering with reflections

带反射的可扩展基于图像的室内场景渲染

• DOI: 10.1145/3476576.3476609
• 发表时间: 2021-07
• 期刊: ACM Transactions on Graphics (TOG)
• 作者: Jiamin Xu;Xuchao Wu;Zihan Zhu;Qixing Huang;Yin Yang;Hujun bao;Weiwei Xu
• 通讯作者: Weiwei Xu

Scene Synthesis via Uncertainty-Driven Attribute Synchronization

• DOI: 10.1109/iccv48922.2021.00558
• 发表时间: 2021-08
• 期刊: 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
• 作者: Haitao Yang;Zaiwei Zhang;Siming Yan;Haibin Huang;Chongyang Ma;Yi Zheng;Chandrajit L. Bajaj;Qi-Xing Huang

MVS2D: Efficient Multiview Stereo via Attention-Driven 2D Convolutions

• DOI: 10.1109/cvpr52688.2022.00838
• 发表时间: 2021-04
• 期刊: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
• 作者: Zhenpei Yang;Zhile Ren;Qi Shan;Qi-Xing Huang