Mahdi Saleh
About Me
I build models that let machines perceive, reconstruct and generate the 3D world.
Hello! I’m Mahdi (also Mehdi) Saleh, a Senior Applied Scientist at Zillow, working on generative AI and 3D foundation models. If you’re a PhD student interested in internships or collaboration, please reach out. I’m always happy to connect.
I completed my PhD at the Technical University of Munich under Federico Tombari and Nassir Navab, graduating summa cum laude. My research spans 3D reconstruction and Gaussian splatting, object pose estimation, and hierarchical 3D representations. I hold a Master’s in Biomedical Computing from TUM and a Bachelor’s in Electrical Control Engineering from IUST. In my free time I enjoy computer graphics, design, web development, and game design.
You can find my latest CV here: CV.
Research Interests
3D foundation models
Generative AI
3D reconstruction and Gaussian splatting
6D object pose estimation
Hierarchical 3D representations
News
- [2026] Paper accepted at IROS 2026 (ODeform project page).
- [2026] Defended my Ph.D. thesis in April, titled Hierarchical Representations for 3D Shape Understanding. The examination committee passed me with distinction; the degree was awarded summa cum laude.
- [2026] Paper accepted at CVPR 2026 (ConceptPose project page).
- [2025] Zillow acquired VSAI; I joined Zillow as a Senior Applied Scientist.
- [2025] Paper accepted at CVPR 2025 (ESCAPE project page).
- [2025] Joined VSAI as Senior Research Engineer.
- [2024] Paper accepted at ICRA 2024.
- [2023] Paper accepted at ICCV 2023.
- [2023] Paper accepted at MICCAI 2023 and 1 paper for ShapeMI MICCAI Workshop.
- [2023] Paper accepted at CVPR 2023.
- [2023] Starting a PhD research internship at Meta Reality Labs, Redmond, WA.
- [2022] Won 2 awards at BOP 6D Object Pose 2022 challenge. Details
- [2022] 1 paper accepted at IROS 2022, Kyoto, Japan.
- [2022] 2 papers accepted at CVPR 2022, New Orleans, USA.
- [2021] 1 paper accepted at NeurIPS 2021.
- [2021] Starting a PhD research internship at Facebook Reality Labs, CA.
- [2021] Recognized as an Outstanding Reviewer at CVPR 2021.
- [2020] Accepted Oral paper at 3DV 2020.
Publications
CVPR 2022
Winner of the BOP 2022 Challenge
ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
3DV 2020
Oral Presentation
Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration
Student Projects
If you are looking for an IDP, guided research, or Master’s thesis around these topics, please contact me.
Here is a list of current and previously supervised projects:
Show supervised projects table — semesters, types, topics, and materials
| Semester | Type | Topic | Student(s) | Material |
|---|---|---|---|---|
| 2023/24 WS | Master’s Thesis | Self-Supervised 3D Shape Completion By Growing Graphs | B. Bekci | |
| 2023 SS | AT3DCV Project | Exploring Unsupervised Multimodal 3D Understanding | I. Unlu, A. Jevtić, O. Aksoy | |
| 2023 SS | AT3DCV Project | Learning Deformations with Hand Interactions | G. Ünver, N. Fest, A. Kolushev | |
| 2023 SS | Master’s Thesis | Enhanced 3D ultrasound visualization through Unsupervised Segmentation | Oleksandra Tmenova | |
| 2022/23 WS | Master’s Thesis | Vertebrae shape completion in ultrasound | M. Gafencu | |
| 2022/23 WS | Master’s Thesis | Real Time Camera Relocalization In Dynamic Environment | E. Shishniashvili | |
| 2022 SS | DI-LAB Project | Partial 3D Thyroid Registration | A. Baumann, V. Burgin, E. Hoppe, H. Y. Kim | Final Report |
| 2022 SS | NLO Project | Case Studies Nonlinear Optimization: Deformable Shape Matching | B. Wu, L. Lüdtke, B. Lipp, P. Massetani | Course Webpage |
| 2022 SS | AT3DCV Project | RANSAC with GNN | A. R. Bhattarai, E. D. Franco, K. Han | |
| 2022 SS | Master’s Thesis | Domain Agnostic Feature Extraction using Graph Neural Networks | R. Srikanth | |
| 2021/22 WS | Guided Research | Self-supervised 3D Detection with Scene Flow | M. Herold, A. Srinivas | |
| 2021/22 WS | Master’s Thesis | 3D Object Detection and Pose Estimation Using Scene Graphs | S. Jeevanandam | |
| 2021/22 WS | Guided Research | Exploring point cloud shape completion and upsampling for 3D object detection | E. Abdelhafez | |
| 2021 SS | Lab Project | Hierarchical Retrieval in 3D Scans using GNN | A. Bodonhelyi, A. Desousa | |
| 2021 SS | Master’s Thesis | PointPerceiver?: Hierarchical point cloud processing with Transformers | Y. Wang | |
| 2021 SS | Master’s Thesis | Weakly-Supervised 3D Object Detection by Self-Ensembling | E. Cakir | |
| 2020/21 WS | Master’s IDP | 3D Object Detection and Flow Estimation in Dynamic Surgical Environments | D. Gokay, E. Simsar | |
| 2020/21 WS | Hiwi | 3D Pedestrian Detection from LiDAR Point Clouds | Ch. Yeshwanth | |
| 2020 SS | Guided Research | 3D Object Detection from Multi-scale Point Clouds Features | N. Danis | |
| 2020 SS | Practical Project | Tabletop Object Trajectory Augmentation using 3D Point Clouds | A. Mehrfard, I. Chan, R. Fok | |
| 2019/20 WS | Master’s IDP | Graph-based Point Cloud Registration for Tool Tracking | Shervin Dehghani | |
| 2019/20 WS | Hiwi Project | Visual Assistance with 3D captioning | HyunJun Jung | |
| 2018/19 WS | Practical Project | Autonomous Garbage Collector using 3D Computer Vision and Reinforcement Learning | HyunJun Jung, Damian Bogunowicz, Sangram Gupta | Final presentation; Video Welcome.AI |
| 2018/19 WS | Practical Project | 3D Reconstruction and Semantic Segmentation for Furniture Replacement | Vasiliki Sideri, Shervin Dehghani, Tam Tran | Final presentation |
| 2018/19 WS | Bachelor’s Thesis | Deep Reinforcement Learning Simulation for Path Planning | Tobias Valinski | |
| 2018/19 SS | Lab Course | 3D Joint Motion Visualization for Sports or Physical Therapy | Sri Divya Vajapeyajula | |
| 2018/19 SS | Lab Course | Live Avatar of 3D Human Pose Tracking | Arturo Diaz Coca | |
| 2018 SS | Bachelor’s IDP | Implementation of Mobile Robot Communication Interface and Sensor Control | Krist S. |
Powered by Jekyll and Minimal Light theme.