Name: Can Gümeli
Position: Ph.D Candidate
E-Mail: can.guemeli@tum.de
Phone: +49 (89) 289 - 18164
Room No: 02.07.038

Bio

My name is Can. I am a Ph.D. Candidate at the Visual Computing Lab, where I am working with Prof. Dr. Matthias Nießner. During my Master's study here at TUM, I have worked on end-to-end CAD model alignment to RGB images at the Visual Computing Lab. As a master's student, I also had an opportunity to work part-time at Intel on high-performance quantum computing simulation. Previously, I obtained my Bachelor's in Computer Engineering from Koç University, Istanbul, Turkey. There I was fortunate to join natural language processing and bioinformatics projects at the AI lab.

Research Interest

CAD Model Alignment and Retrieval, Semantic SLAM, 3D Reconstruction

Publications

2025
PrEditor3D: Fast and Precise 3D Shape Editing
Ziya Erkoç, Can Gümeli, Chaoyang Wang, Matthias Nießner, Angela Dai, Peter Wonka, Hsin-Ying Lee, Peiye Zhuang
CVPR 2025
We propose a training-free approach to 3D editing that enables the editing of a single shape within a few minutes. The edited 3D mesh aligns well with the prompts, and remains identical for regions that are not intended to be altered. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling fast, high-quality editing while preserving unintended regions.
[video][bibtex][project page]
2023
ObjectMatch: Robust Registration using Canonical Object Correspondences
Can Gümeli, Angela Dai, Matthias Nießner
CVPR 2023
ObjectMatch leverages indirect correspondences obtained via semantic object identification. For instance, when an object is seen from the front in one frame and from the back in another frame, ObjectMatch provides additional pose constraints through canonical object correspondences. We first propose a neural network to predict such correspondences, which we then combine in our energy formulation with state-of-the-art keypoint matching solved with a joint Gauss-Newton optimization. Our method significantly improves state-of-the-art feature matching in low-overlap frame pairs as well as in the registration of low frame-rate SLAM sequences.
[video][bibtex][project page]
2022
ROCA: Robust CAD Model Retrieval and Alignment from a Single Image
Can Gümeli, Angela Dai, Matthias Nießner
CVPR 2022
We present ROCA, a novel end-to-end approach that retrieves and aligns 3D CAD models to a single RGB image using a shape database. Thus, our method enables 3D understanding of an observed scene using clean and compact CAD representations of objects. Core to our approach is our differentiable alignment optimization based on dense 2D-3D object correspondences and Procrustes alignment.
[video][code][bibtex][project page]