Publications by Zheng Dang | EPFL Graph Search

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches have shown remarkable success on synthetic datasets, we have observed them to fail in the presence of real-world data. We ...

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether using the SVD to compute them analytically or using the Power Iteration (PI) ...

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive, and time-consum ...

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in the presence of r ...

In this paper, we propose a novel center-based decoupled point cloud registration framework for robust 6D object pose estimation in real-world scenarios. Our method decouples the translation from the entire transformation by predicting the object center an ...

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

Determining the relative pose of an object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically approximate the continuous pose representation with a large number of discrete pose hypotheses, w ...

In this work, we tackle the problem of 7-DoF grasping pose estimation(6-DoF with the opening width of parallel-jaw gripper) from point cloud data, which is a fundamental task in robotic manipulation. Most existing methods adopt 3D voxel CNNs as the backbon ...

Zheng Dang

Chat with Graph Search

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

Match Normalization: Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Robust Differentiable SVD

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration

Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World

Center-Based Decoupled Point Cloud Registration for 6D Object Pose Estimation

Robust Outlier Rejection for 3D Registration with Variational Bayes

Dvmnet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

Multi-Source Fusion for Voxel-Based 7-DoF Grasping Pose Estimation