I'm a master's student in Computer Science at the Technical University of Munich, Germany. I'm interested in Machine Learning and have worked with functional map methods for spectral shape correspondences related with geometry processing and 3D computer graphics/vision.

Previously, I completed my Bachelor's at Xi'an Jiaotong University, while also having visited the University of California, Berkeley for a semester exchange.

Currently, I'm seeking PhD opportunities with a focus on Machine Learning.

Outside of study, I 🤖enjoy sci-fi and Nolan films.


Research

EchoMatch: Partial-to-Partial Shape Matching via Correspondence Reflection

Yizheng Xie*, Viktoria Ehm*, Paul Roetzer, Nafie El Amrani, Maolin Gao, Florian Bernard, Daniel Cremers

CVPR 2025

Novel overlap predictor, improved IoU performance on all challenging benchmarks by avg. 12%.

Beyond Complete Shapes: A Quantitative Evaluation of 3D Shape Matching Algorithms

Viktoria Ehm*, Nafie El Amrani*, Yizheng Xie, Lennart Bastian, Maolin Gao, Weikang Wang, Lu Sang, Dongliang Cao, Daniel Cremers, Zorah Lähner, Florian Bernard

2025

A comprehensive framework, benchmark and evaluation for partial 3D shape matching.

Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching

Lennart Bastian*, Yizheng Xie*, Nassir Navab, Zorah Lähner

CVPR 2024

A novel approach of hybridizing basis functions originating from different operators, resulting in hybrid functional maps for shape correspondence tasks, improving performance in near-isometric, non-isometric, and topologically noisy settings.

Seminar

An Introductory Perspective on Functional Maps

Aims to provide an intuitive understanding of this representation, its significance, and its applications for non-rigid shape matching.

Thanks to Nicholas Sharp for the excellent template that this page is based on.