Search Results for author:
Found 14 papers, 4 papers with code
DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses
Determining the relative pose of an object between two images is pivotal to the success of generalizable object pose estimation.
DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration
We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth.
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration
Specifically, AutoSynth automatically curates an optimal dataset by exploring a search space encompassing millions of potential datasets with diverse 3D shapes at a low cost. To achieve this, we generate synthetic 3D datasets by assembling shape primitives, and develop a meta-learning strategy to search for the best training data for 3D registration on real point clouds.
Robust Outlier Rejection for 3D Registration with Variational Bayes
Embedded with the inlier/outlier label, the posterior feature distribution is label-dependent and discriminative.
Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation
Our method decouples the translation from the entire transformation by predicting the object center and estimating the rotation in a center-aware manner.
MatchNorm: Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World
Our two contributions are general and can be applied to many existing learning-based 3D object registration frameworks, which we illustrate by implementing them in two of them, DCP and IDAM.
What Stops Learning-based 3D Registration from Working in the Real World?
We summarise our findings into a set of guidelines and demonstrate their effectiveness by applying them to different baseline methods, DCP and IDAM.
Robust Differentiable SVD
Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms.
3D Registration for Self-Occluded Objects in Context
While much progress has been made on the task of 3D point cloud registration, there still exists no learning-based method able to estimate the 6D pose of an object observed by a 2. 5D sensor in a scene.
A Method to Generate High Precision Mesh Model and RGB-D Datasetfor 6D Pose Estimation Task
Recently, 3D version has been improved greatly due to the development of deep neural networks.
Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration
While 3D-3D registration is traditionally tacked by optimization-based methods, recent work has shown that learning-based techniques could achieve faster and more robust results.
Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems
In this paper, we introduce an eigendecomposition-free approach to training a deep network whose loss depends on the eigenvector corresponding to a zero eigenvalue of a matrix predicted by the network.
Backpropagation-Friendly Eigendecomposition
Eigendecomposition (ED) is widely used in deep networks.
Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix representing a linear system.
