Geometric Uncertainty

Geometric uncertainty, encompassing inaccuracies in shape, pose, and other geometric properties, poses a significant challenge across various fields, from robotics to medical imaging. Current research focuses on developing methods to model and mitigate this uncertainty, employing techniques like differentiable contact dynamics, convex hull analysis of training data, and probabilistic deep learning models (e.g., multi-head networks, generative adversarial networks) to improve robustness and accuracy in applications. These advancements are crucial for enhancing the reliability of autonomous systems, improving the precision of 3D modeling and reconstruction, and enabling more effective design and manufacturing processes.

Papers

September 26, 2024

Stable Object Placement Under Geometric Uncertainty via Differentiable Contact Dynamics
Linfeng Li, Gang Yang, Lin Shao, David Hsu
Object Placement Geometric Uncertainty

May 25, 2024

Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets
Hyekyoung Hwang, Jitae Shin
Deep Learning Deep Neural Network Adversarial Attack Deep Learning System Convex Hull Uncertainty Measure Training Set Geometric Uncertainty

May 21, 2024

Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos
Jayroop Ramesh, Nicola K Dinsdale, the INTERGROWTH-21st Consortium, Pak-Hei Yeung, Ana IL Namburete
Localization Accuracy 3D Brain Fetal Brain Uncertainty Aware Deep Learning Geometric Uncertainty

April 21, 2024

SpringGrasp: Synthesizing Compliant, Dexterous Grasps under Shape Uncertainty
Sirui Chen, Jeannette Bohg, C. Karen Liu
Grasp Planning Robust Grasp Geometric Uncertainty Compliant Robotic Grasping

October 24, 2023

GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
Yan Lu, Xinzhu Ma, Lei Yang, Tianzhu Zhang, Yating Liu, Qi Chu, Tong He, Yonghui Li, Wanli Ouyang
3D Detection Monocular 3D Object Detection Uncertainty Propagation Perspective Projection Depth Estimation Error Geometric Uncertainty

February 21, 2022

GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty
Wei Wayne Chen, Doksoo Lee, Oluwaseyi Balogun, Wei Chen
Product Design Robust Optimization Generative Adversarial Geometric Optimization Ct Gan Geometric Uncertainty Hierarchical Deep Generative

Geometric Uncertainty

Papers

Stable Object Placement Under Geometric Uncertainty via Differentiable Contact Dynamics

Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets

Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos

SpringGrasp: Synthesizing Compliant, Dexterous Grasps under Shape Uncertainty

GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection

GAN-DUF: Hierarchical Deep Generative Models for Design Under Free-Form Geometric Uncertainty