Yipeng Sun, M. Sc.

Researcher

Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 10.137
Martensstr. 3
91058 Erlangen

  • Since 07/2023:
    Ph.D. Student at Pattern Recognition Lab, FAU Erlangen-Nürnberg
  • 10/2020 – 06/2023:
    M.Sc. Medical Engineering, FAU Erlangen-Nürnberg
  • 09/2015 – 07/2019:
    B.Eng. Measurement & Control Technology & Instrument, Nanjing University of Science and Technology

2023

  • An AI-based framework for visualizing and analyzing massive amounts of 4D tomography data for beamline end users

    (Third Party Funds Group – Overall project)

    Project leader: ,
    Term: March 1, 2023 - February 28, 2026
    Acronym: KI4D4E
    Funding source: Bundesministerium für Forschung, Technologie und Raumfahrt (BMFTR)
    URL: https://foerderportal.bund.de/foekat/jsp/SucheAction.do?actionMode=view&fkz=05D23WE1
    Abstract

    Synchrotron tomography is characterized by extremely brilliant X-rays, which enables almost artifact-free imaging. Furthermore, very high resolution can be achieved by using special X-ray optics, and the special design of synchrotron facilities also allows fast in-situ experiments, i.e. 4D tomography.  The combination of these features enables high-resolution computed tomography on objects where conventional laboratory CT fails. At the same time, however, this also produces enormous amounts of data that are generally unprocessable by end users, pushing even the operators of synchrotrons to their limits.

    The goal of the KI4D4E project is to develop AI-based methods that can be used by end users to process the enormous amounts of data in such 4D CT measurements. This includes improving image quality through artifact reduction, reduction and accessibility of data to end users to help the latter interpret the results.

    The project focuses on the topics of artifact reduction, segmentation and visualization of large 4D data sets. The resulting methods should be applicable to data from both photon and neutron sources.

2026

Conference Contributions

2025

Journal Articles

Conference Contributions

2024

Conference Contributions

2023

Conference Contributions

Type Title Status
MA thesis Robust CT image restoration based on evolutionary algorithms running
MA thesis Autoregressive Model Based on the Hilbert Curve for CT Artifact Removal running
MA thesis A Cascaded Encoder–Decoder Network for CT Image Restoration running
MA thesis Large Kernel Convolution for CT Image Restoration running
MA thesis Cold Diffusion for CT Field-of-View Extension running
MA thesis Evolving Universal Datasets: Cross-Architecture Generalization via Evolutionary Distillation finished
MA thesis A Reasoning Agent for Chest X-ray with Memory finished
MA thesis Diffusion Transformer for CT artifacts compensation finished
Project CT Field-of-View Extension Dataset Simulation finished
MA thesis Category-Level Segmentation of industrial Parts Using SAM2 Memory System finished
Project Frequency Domain Hierarchical Vision Transformer-based Perceptual Loss finished
MA thesis Universal Image Artifact Reduction via Heterogeneous Mixture of Experts finished
Project 3D CT Image Visualization using Blender running
Project Artifacts Simulation in CT Images finished
Project Diffusion Model-Enabled Energy Level Transformation in Photon Counting Computed Tomography (PCCT) finished
Project A Comparative Analysis of Loss Functions in Deep Learning-Based Inverse Problems finished
MA thesis Deep Learning Computed Tomography based on the Defrise and Clack Algorithm for Specific CBCT Orbits finished
Project Investigating the Possibilities of CT Reconstruction using Fourier Neural Operator finished