Publications (16)
Rethinking Attention Module Design for Point Cloud Analysis
Chengzhi Wu, Kaige Wang, Zeyun Zhong +5
In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research…
A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning
Chengzhi Wu, Qianliang Huang, Kun Jin +2
Contrastive learning is an essential method in self-supervised learning. It primarily employs a multi-branch strategy to compare latent representations obtained from different bran…
Self-Supervised Generative-Contrastive Learning of Multi-Modal Euclidean Input for 3D Shape Latent Representations: A Dynamic Switching Approach
Chengzhi Wu, Julius Pfrommer, Mingyuan Zhou +1
We propose a combined generative and contrastive neural architecture for learning latent representations of 3D volumetric shapes. The architecture uses two encoder branches for vox…
Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
Laura von Rueden, Sebastian Mayer, Katharina Beckh +11
Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge…
Sim2real Transfer Learning for Point Cloud Segmentation: An Industrial Application Case on Autonomous Disassembly
Chengzhi Wu, Xuelei Bi, Julius Pfrommer +3
On robotics computer vision tasks, generating and annotating large amounts of data from real-world for the use of deep learning-based approaches is often difficult or even impossib…
SynMotor: A Benchmark Suite for Object Attribute Regression and Multi-task Learning
Chengzhi Wu, Linxi Qiu, Kanran Zhou +2
In this paper, we develop a novel benchmark suite including both a 2D synthetic image dataset and a 3D synthetic point cloud dataset. Our work is a sub-task in the framework of a r…
Partially Observable Gaussian Process Network and Doubly Stochastic Variational Inference
Saksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer
To reduce the curse of dimensionality for Gaussian processes (GP), they can be decomposed into a Gaussian Process Network (GPN) of coupled subprocesses with lower dimensionality. I…
Attention-based Part Assembly for 3D Volumetric Shape Modeling
Chengzhi Wu, Junwei Zheng, Julius Pfrommer +1
Modeling a 3D volumetric shape as an assembly of decomposed shape parts is much more challenging, but semantically more valuable than direct reconstruction from a full shape repres…
Dynamic vehicle redistribution and online price incentives in shared mobility systems
Julius Pfrommer, Joseph Warrington, Georg Schildbach +1
This paper considers a combination of intelligent repositioning decisions and dynamic pricing for the improved operation of shared mobility systems. The approach is applied to Lond…
Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization
Saksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer
Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing with high-dimensional multi-stag…
6D Pose Estimation on Point Cloud Data through Prior Knowledge Integration: A Case Study in Autonomous Disassembly
Chengzhi Wu, Hao Fu, Jan-Philipp Kaiser +5
The accurate estimation of 6D pose remains a challenging task within the computer vision domain, even when utilizing 3D point cloud data. Conversely, in the manufacturing domain, i…
Object Detection in 3D Point Clouds via Local Correlation-Aware Point Embedding
Chengzhi Wu, Julius Pfrommer, Jürgen Beyerer +2
We present an improved approach for 3D object detection in point cloud data based on the Frustum PointNet (F-PointNet). Compared to the original F-PointNet, our newly proposed meth…
Attention-based Point Cloud Edge Sampling
Chengzhi Wu, Junwei Zheng, Julius Pfrommer +1
Point cloud sampling is a less explored research topic for this data representation. The most commonly used sampling methods are still classical random sampling and farthest point…
Virtual Process Dossier: A Process-Aware Data Catalogue
Lukas Kubelka, Alexander Bott, Frank Döhner +6
The paper introduces the Virtual Process Dossier (VPD), a knowledge‑graph based data catalogue that records workflow provenance for multi‑stage manufacturing, enabling FAIR data ac…
SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity
Chengzhi Wu, Yuxin Wan, Hao Fu +5
Driven by the increasing demand for accurate and efficient representation of 3D data in various domains, point cloud sampling has emerged as a pivotal research topic in 3D computer…
MotorFactory: A Blender Add-on for Large Dataset Generation of Small Electric Motors
Chengzhi Wu, Kanran Zhou, Jan-Philipp Kaiser +7
To enable automatic disassembly of different product types with uncertain conditions and degrees of wear in remanufacturing, agile production systems that can adapt dynamically to…