Visual Odometry with new Unprecedented Event Camera
In this project, you will explore and implement new algorithms for visual odometry (VO) with a new prototype event camera with unprecedented performance. This new and unexplored sensor has a high potential to improve upon existing works in the field of VO.
The link between spread of alpha-synuclein, structural connectivity alteration and neurodegeneration in a-synuclein mouse model
Elucidating the temporal and spatial relation of alpha-synuclein accumulation related pathological changes, aberrant brain structural connectivity and neurodegeneration are important for understanding the mechanism of Parkinson’s disease.
Event-based Structured Light for Depth Sensing and Material Differentiation in Forest Canopies
This project will investigate the used of event-camera based depth sensing using structured light in the challenging environment of forest canopies. Additionally, utilizing the unique properties of event cameras, material differentiation based on spectral responses will be developed.
Develop a diagnostic biosensor
Develop a low-cost and sensitive diagnostic biosensor. You will work on a new sensor technology applicable for various diseases including cronic diseases, cancer or covid-19. The project is ideal for skilled students who are passionate to work on an interdisciplinary project with immediate impact.
Assay developement for cancer diagnostics
You will develop a diagnostic test for testicular cancer. The focus of the project will be on creating the biochemical protocols for the test. The project is in collaboration with a prelaunch startup and a hospital (USZ). Therefore, it is ideal for motivated students who want to have a direct impact
Invitation to apply for an SNSF Swiss Postdoctoral Fellowship in MRI of the developing human brain circuitry
We are inviting applicants to apply for an SNSF Swiss Postdoctoral Fellowship to join our research group. The research project would be hosted at the University of Zürich in Switzerland. The fellowship is the Swiss equivalent of the prestigious Marie-Sklodowska Curie Postdoctoral Fellowship. After the selection of one or two promising candidates and identification of the focus of research, we will support you in the application process.
Study on the effects of camera resolution in Visual Odometry
Study on the effects of camera resolution in Visual Odometry
Deep line detection for autonomous navigation
Learning-based robust line detection algorithm for autonomous navigation.
Research Assistant/PhD Student in Computer Science, Visualization, Data Science
Open position for a PhD student in the project Uncertainty Visualization and Analysis of High-Resolution Numeric Weather Forecasts at the University of Zürich. This position is for a PhD student participating in a SNF (Swiss National Science Foundation) funded joint project between the University of Zürich (UZH) and the University of Buenos Aires (UBA).
Data-driven Keypoint Extractor for Event Data
The project aims to develop a data-driven keypoint extractor, which computes interest points and descriptors. Based on the current advances of learned keypoint extractors for traditional frames, the approach will leverage neural network architectures to extract and describe keypoints in an event stream.
Domain Transfer between Events and Frames
In this project, the student extends current advances from the UDA literature for traditional frames to event data in order to transfer multiple tasks from frames to events. The approach should be validated on several tasks in challenging environments (night, high-dynamic scenes) to highlight the benefits of event cameras.
Neural Network Representation for Vision-Based MPC Control
Train a neural network to predict an intermediate representation from an image that can be used by an MPC to avoid obstacles.
Learned Low-Level Controller
Neural networks are renowned for their expressiveness. In this project, we study their application as a low-level controller on a drone.
In-silico cardiac and cardiovascular modelling with physics informed neural networks
The aim of the project is to investigate the benefits, requirements and drawbacks of physics informed neural networks in the context of personalised cardiac and cardiovascular models
Develop the electronics for a new medical sensor
You will work on bringing medical tests to peoples home. You will further develop the hardware and software for a readout device that can perform a variety of diagnostic tests in a reliable but simple fashion.
3D reconstruction with event cameras
This project will explore the application of event camera setups for scene reconstruction. Accurate and efficient reconstructions using event-camera setups is still an unexplored topic. This project will focus on solving the problem of 3D reconstruction using active perception with event cameras​.
Event-based depth estimation​
This project will focus on event-based depth estimation using structured light systems.
Sensor Fusion for Drone Racing
Sensor Fusion for Drone Racing
Learned Perception for Drone Racing
Learned Perception for Drone Racing
Deep Learning for Vision-Based State Estimation in Drone Racing
Deep Learning for Vision-Based State Estimation in Drone Racing
Vision for human-piloted Drone Racing
Vision for human-piloted Drone Racing
Learning to calibrate an event camera
This work will address intrinsic calibration of event cameras, a fundamental problem for application of event cameras to many computer vision tasks, by incorporating deep learning.
Vision-based Dynamic Obstacle Avoidance
Dynamic obstacle avoidance is a grand challenge in vision-based drone navigation. The classical mapping-planning-control pipeline might have difficulties when facing dynamic objects.
Event-based Vision for Autonomous Driving
Collaborate with Volkswagen's research division to create a high-quality driving dataset including event cameras
Computational Photography and Videography
Combine the complementary information from standard and event cameras to enhance images and video.
Optimization for Spiking Neural Networks
An exploration of optimization methods for spiking neural networks
4D force map of Cardiomyocytes contractility
This Project combines two innovative force sensing technique in order to resolve the Cardiomyocyte contractility with high sensitivity. The aim of the this project to study the mechano-electric coupling of the Cardiomyocyte during various stimulation.
Investigating cell mechanics with FluidFM force spectroscopy
This project aims to investigate the mechanical properties of living cells using FluidFM technique combined with novel optical tools.
Efficient Learning-aided Visual Inertial Odometry
Online learning-aided visual inertial odometry for robust state estimation
State Estimation for Drone Racing
State Estimation for Drone Racing
Next-Generation DNA-Based Biomedical Sensors
Our goal is to develop paradigm-shifting electronic biosensors to detect neurochemicals released in the brain and biomarkers in clinically relevant human fluids. These novel biosensors will help us answer relevant neuroscience questions and tackle human health concerns.
Deep Learning for Estimation using New Sensors in our Drones
Quadcopter platforms have been gaining popularity in recent years due to their maneuverability and uncomplicated design. Recent advances in hardware components, such as motors and electronic speed controllers (ESCs), unlock different possible extensions of the classical quadcopter design to gain new capabilities. In this project, we aim to modify the current design of our platform to build a quadcopter equipped with new sensing modalities. This will allow new ways of performing control, modeling and even state estimation.
Multiplex fluorescence imaging of human tissue
In situ interrogation of dozens of molecules including proteins and RNAs by multiplex imaging in their native 3D tissue volume depicts the original spatial localization of complex tissue components and holds extensive applications in biomedical research. Here we would develop a simple and robust multiplex 3D imaging method based on new readout and tissue clearing to achieve highly multiplex 3D molecular mapping of human biopsy. Single cell spatial relationship and cell-cell interactions in 3D niche would be analysed using advanced computational methods.
Development of the first rapid antigen test to detect flesh-eating bacteria.
You will develop a new diagnostic lateral flow test to detect Mycobacterium ulcerans, slowly growing flesh-eating bacteria that cause Buruli ulcer (BU) disease. The BU is a neglected tropical disease often leading to severe suffering, stigmatization and permanent disabilities in children in West Africa. Field-applicable rapid antigen test is currently missing, and its urgent development is one of WHO priorities in BU's successful treatment. You will optimize individual components of LFA to develop highly sensitive diagnostic tests for clinical application. You will work on an interdisciplinary project in collaboration with ETH spin-off Hemetron AG. This fast pace project is ideal for highly motivated students.
Vocal repertoire of Norwegian killer whales (Orcinus orca)
Be part of an interdisciplinary team and contribute to a project investigating the vocal repertoire of free-ranging killer whale calls using bioacoustics and machine learning techniques.
Spin diffusion in nanoparticles
The aim of this project is to study the nuclear spin diffusion in semiconducting nanoparticles as a potential next generation hyperpolarized imaging agent
Optimization of spectral-spatially selective RF excitation pulses for hyperpolarized 13C MRI
The aim of this project is to design, implement and test novel multiband RF excitation pulses for hyperpolarized metabolic MRI of the heart using simulations, phantom experiments and possibly in-vivo testing.
Ph.D. position in RNA biology / biophysics
In any kingdom of life, the splicing process, in which the non-coding sequence (intron) is excised from the coding part (exon), is one of the major steps during RNA maturation. In bacteria, archaea, and mitochondria, this function is entirely carried out by RNA, whereas in the nucleus, the splicing is supported by a huge machinery of proteins called the spliceosome. However, both mechanisms are evolutionarily related. Understanding the underlying function and structure of the catalytic active RNA (intron) is essential to elucidate the evolutionary relationship between both.
Reinforcement Learning for Drone Racing
Reinforcement Learning for Drone Racing
Master Thesis: Pitch tracking of killer whale calls
Be part of an interdisciplinary team and contribute to a signal processing project about pitch tracking of killer whale calls. The goal is a publication about the new method that we develop and test in various example cases.
Multi-agent Drone Racing via Self-play and Reinforcement Learning
Drone racing requires human pilots to not only complete a given race track in minimum-time, but also to compete with other pilots through strategic blocking, or to overtake opponents during extreme maneuvers. Single-player RL allows autonomous agents to achieve near-time-optimal performance in time trial racing. While being highly competitive in this setting, such training strategy can not generalize to the multi-agent scenario. An important step towards artificial general intelligence (AGI) is versatility -- the capability of discovering novel skills via self-play and self-supervised autocurriculum. In this project, we tackle multi-agent drone racing via self-play and reinforcement learning.
Co-occurrence of Interictal Epileptiform Discharges (IEDs) and High Frequency Oscillations (HFOs) in intracranial EEG.
Epilepsy is characterized by seizures. Therapy aims for seizure freedom or seizure reduction. Since seizures are rare events, diagnostic tools analyze the time between seizures, the interictal period. Interictal Epileptiform Discharges (IED) are a traditional and sensitive marker for epileptogenic brain tissue, which are, however, not very specific. More recently, High Frequency Oscillations (HFO) were defined as a more specific marker, which is, however, hard to detect The combination of IED and HFO is thought to improve diagnostic accuracy. In a recent publication that analyzed scalp EEG, the combined presence of IED and HFO enhanced the localization of epileptogenic brain tissue (Cai et al. , 2021). We have published data where intracranial EEG was recorded in patients that were candidates for epilepsy surgery (Fedele et al. , 2017). In the proposed project, we analyze intracranial EEG that was recorded while patients were in deep sleep (Fedele et al. , 2017). We test whether the combined presence of IED and HFO improves the prediction accuracy of postoperative seizure freedom. Baud MO, Kleen JK, Anumanchipalli GK, Hamilton LS, Tan YL, Knowlton R, Chang EF. Unsupervised Learning of Spatiotemporal Interictal Discharges in Focal Epilepsy. Neurosurgery. 2018;83:683-91. https://doi.org/10.1093/neuros/nyx480 Cai Z, Sohrabpour A, Jiang H, Ye S, Joseph B, Brinkmann BH, Worrell GA, He B. Noninvasive high-frequency oscillations riding spikes delineates epileptogenic sources. Proc Natl Acad Sci U S A. 2021;118. https://doi.org/10.1073/pnas.2011130118 Fedele T, Burnos S, Boran E, Krayenbühl N, Hilfiker P, Grunwald T, Sarnthein J. Resection of high frequency oscillations predicts seizure outcome in the individual patient. Scientific Reports. 2017;7:13836. https://doi.org/10.1038/s41598-017-13064-1
Optimising a biosensor of cellular age
Ageing is commonly defined as the time-dependent deterioration in organismal fitness. However, variability in ageing kinetics has led to the hypothesis that each cell type possesses its own ageing trajectory. We currently develop novel ageing biosensors to characterize the progression of cellular age across different murine cell types and tissues. The aim of the project is to modify the existing sensors allowing for real-time analysis of cellular age in diverse cell types.
Co-development of novel diagnostic device for at-home blood testing.
In this project, you will further optimize a lateral flow assay (LFA) compatible with our novel highly sensitive electrochemical readout that will form a cornerstone for the ground-breaking point-of-need diagnostics device. Under our supervision, you will be working on an assay development with a focus, amongst others, on decreasing the non-specific binding of analyte and gold nanoparticles to the LFA membrane matrix, increasing sensitivity by optimizing the chemical environment of the immune-sandwich formation, nanoparticle/receptor conjugation or capillary flow optimization. You will work on an interdisciplinary project in collaboration with ETH spin-off Hemetron (https://www.hemetron.com/, https://www.linkedin.com/company/hemetron/). This fast pace project is ideal for highly motivated students.
Gravity line based surgical planning for spinal deformity corrections
This project is about the implementation of an algorithm based on the patient's gravity line to help plan spinal deformity corrections.
Semester Project / Master Thesis: Priming of mesenchymal stem cells for immunomodulatory cell therapy
Mesenchymal stem cells (MSCs) have an exceptional clinical potential, with possible applications in various inflammatory and degenerative diseases such as in osteoarthritis or disc degeneration. Preconditioning of MSCs (also known as priming) is a commonly used method to enhance the efficacy of MSCs. Various priming strategies exist, including pro-inflammatory priming and 3D culture priming. Little is known about how well MSCs can preserve this priming effect over time.
Postdoctoral Position in Systems Neuroscience
In vivo Imaging of Hippocampal Ensemble Coding, Memory Consolidation and Sleep Disturbances in Neurodegenerative Diseases
Computational Fluid Dynamics of Blood Flow in the Aorta
The aim of this project is to investigate and characterize flow patterns in various patient-specific aortic geometries using CFD.
Automatic classification of severity of calcific aortic valve disease in synthetic 4D flow MRI data
The aim of this project is to train a neural network for classification of the severity of calcific aortic valve disease applied to 4D flow MRI data.
Automatic unwrapping of PC-MRI velocity maps with Neural Networks
The aim of this project is to develop an automatic method to correct for aliasing in phase-contrast MR images.
Deep Learning for Valve Tracking in Cardiac MRI
This project is concerned with developing a machine learning approach (for example, using convolutional neural networks) for localising, segmenting and tracking the aortic valve in cardiac MR images.
Development of Deep Learning Methods for routine Dermatology consultation
Department of Dermatology at the University Hospital Zurich is currently offering various Master and Bachelor thesis projects in clinical applications of deep learning algorithms.
Pick and Place of Neurons with FluidFM
FluidFM is an innovative technology that can be used to create cell structures and formations in lab-on-chip devices, as well as positioning cellular microstructures for experimental configurations or bioprinting. It comprises a hollow atomic force microscopy (AFM) cantilever within which a positive or a negative pressure can be generated and used to pick up and put down single cells. The technology can also be used to measure adhesion forces in cells, for injection into single cells and for the extraction of cellular contents from cells.
Bachelor / Master Theses or Semester Project in X-ray Tomography
X-ray tomography group of Prof. Dr. Marco Stampanoni invites current Bachelor and Master students to do your thesis or semester project in our team.
Contrastive Representation Learning for Time Series
Time series analysis plays an important role in various industries such as medical informatics, healthcare, financial market, and climate modeling. Recent development in machine learning has promised to revolutionize predicting and classifying time sequences, by means of temporal convolutional networks and transformers. Although many state-of-the-art models have reached good performance in time series forecasting and classification, many time series tasks remain a challenge. Our research interest lies in time series representation learning, which aims to capture both contextual and temporal information at any resolution and generate representations to improve multiple downstream tasks (patient sequence similarity, etc.).
Robot Primate to study Imitation Learning (ETH Neurotechnology Group)
Human-level imitation learning remains to be the greatest frontier in robotics. We are interested in understanding the computations in the primate brain during imitation and would like to build a robotic avatar of a marmoset monkey, with which a real monkey can interact.
Patient Motion Modeling for Robust Magnetic Resonance Imaging
Patient motion is one of the main causes of artifacts in MR imaging. The aim of this project is to develop image reconstruction algorithms that include data-driven motion compensation techniques.
PhD Position on Stimulated Raman Scattering Microscopy
The group of Experimental Imaging and Neuroenergetics (Prof. Bruno Weber) at the University of Zurich is seeking a PhD student for a new project on Stimulated Raman Scattering (SRS) microscopy. The lab has longstanding experience in in-vivo (mainly two-photon) imaging technologies (calcium, FRET, FLIM, SHG/THG) combined to stimulation protocols in anesthetized and awake mice. As part of our investigations, we are interested in the distribution and consumption of glucose in different cell types in the brain. The implementation of SRS, combined with specially designed glucose derivatives, is a very powerful tool to address such questions in a minimally invasive way, while at the same time producing advanced structural information. The project will focus on the implementation of the technique in one of our custom-built multi-photon microscopes, involving precise optical alignment and fast beam modulation, detector design, advanced lock-in amplification-based detection strategies and data analysis (including deep-learning based denoising strategies). The ideal candidate should have a background in engineering or physics, with strong interest in the application of measurement hardware and advanced data analysis for the implementation of new technologies in life science experiments. We offer a cutting-edge experimental infrastructure and a dedicated supervision in a multidisciplinary team at Irchel Campus of UZH.
3D reconstruction from bi-planar radiographs
Development of a pipeline for learning-based 3D reconstruction from bi-planar radiographs using anatomical mesh templates.
Advancing novel methods in diffusion MRI
Diffusion MRI is a leading technique for the noninvasive assessment and quantification of tissue microstructure, driving an improved understanding of tissue anatomy. The aim of this project is to assess and/or further develop novel methods in diffusion MRI, particularly those used in human brain imaging.
Multimodal Multilingual NLP in Medicine
Multimodal Multilingual NLP in Medicine
Development of a platform for automatic detection of spinal diseases for FE-modelling.
Development of a platform for automatic detection of spinal diseases and 3D segmentation of spinal discs.

Powered by  SiROP - the academic career network