Search
Search Results
-
Geometric constraints based 3D reconstruction method of tomographic SAR for buildings
The mainstream methods of tomographic synthetic aperture radar (tomoSAR) 3D reconstruction are usually realized by processing the registered 2D SAR...
-
Self-supervised learning of monocular 3D geometry understanding with two- and three-view geometric constraints
The 3D geometry understanding of dynamic scenes captured by moving cameras is one of the cornerstones of 3D scene understanding. Optical flow...
-
Geometric Pose Affordance: Monocular 3D Human Pose Estimation with Scene Constraints
Accurate estimation of 3D human pose from a single image remains a challenging task despite many recent advances. In this paper, we explore the... -
Visual SLAM Algorithm Based on Target Detection and Direct Geometric Constraints in Dynamic Environments
To enhance the localization accuracy and robustness of the visual SLAM algorithm in dynamic environments, this paper proposes a methodology that... -
Fast and Accurate 3D Registration from Line Intersection Constraints
3D Registration is a fundamental part of several robotics and automation tasks. While classical methods predominantly exploit constraints from points...
-
Neural 3D reconstruction from sparse views using geometric priors
Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation. Existing methods usually...
-
GRAMO: geometric resampling augmentation for monocular 3D object detection
Data augmentation is widely recognized as an effective means of bolstering model robustness. However, when applied to monocular 3D object detection,...
-
Construction of Pseudo-Geometric Integrators
AbstractIn this paper, we consider the problem of constructing higher-order geometric integrators. In particular, we study the situations where the...
-
Convex-Geometric k-Planar Graphs Are Convex-Geometric \((k+1)\) -Quasiplanar
A drawing of a graph is k-planar if every edge has at most k crossings with other edges of the graph and it is k-quasiplanar if it has no set of k... -
Geometric algebra-based multiscale encoder-decoder networks for 3D motion prediction
3D human motion prediction is one of the essential and challenging problems in computer vision, which has attracted extensive research attention in...
-
Brain Cortical Surface Registration with Anatomical Atlas Constraints
This work presents a novel cortical surface registration framework by using the whole anatomical atlas structures as correspondence constraints,... -
Adversarial Geometric Transformations of Point Clouds for Physical Attack
Towards adversarial physical attack in real world, we argue that the main challenge lies in discounting adversarial effects by changes of point... -
CVAE-LAYOUT: automatic furniture layout with constraints
We propose an automatic layout method for indoor scenes that effectively satisfies specific constraints. Our approach involves enhancing the existing...
-
Geometric Constraints for Self-supervised Monocular Depth Estimation on Laparoscopic Images with Dual-task Consistency
Depth values are essential information to automate surgical robots and achieve Augmented Reality technology for minimally invasive surgery. Although... -
Virtual Affine Nonholonomic Constraints
Virtual constraints are relations imposed on a control system via feedback control that become invariant via feedback, as opposed to physical... -
Large Language Model for Geometric Algebra: A Preliminary Attempt
Geometric algebra serves as the unified language of mathematics, physics, and engineering in the 21st century. Coinciding with the era of artificial... -
Improving generalization for geometric variations in images for efficient deep learning
Deep Learning models for tasks such as image classification have a hard time adapting to the unseen geometric variations (such as scale, perspective,...
-
Normal map** and normal transfer for geometric dynamic models
Normal map** is one of the most important realistic rendering techniques that preserve geometric attribute values on the simplified model. There...
-
Self-evident Automated Geometric Theorem Proving Based on Complex Number Identity
How to automatically generate short and easy-to-understand proofs for geometric theorems has long been an issue of concern in mathematics education....
-
Monocular visual-inertial odometry leveraging point-line features with structural constraints
Structural geometry constraints, such as perpendicularity, parallelism and coplanarity, are widely existing in man-made scene, especially in...