Institute for Intelligent Interactive Systems

Open Opportunities

Optical sensor development and optimization for physiological sensing ETH Zurich Sensing, Interaction & Perception Lab What optimizations are necessary to make reflective PPG sensors reliably work on tissue with limited blood perfusion? Electrical and Electronic Engineering, Information, Computing and Communication Sciences Bachelor Thesis, Master Thesis, Semester Project

Android/iOS live interface for visualizing streaming wearable sensor data ETH Zurich Sensing, Interaction & Perception Lab Wearables are all the rage. They collect a lot of data, but it's not clear what that data looks like. What do wearables 'see' when we move, when we walk, talk, or jump? What is the depth of our vital parameters that they can observe? Computer Communications Networks, Computer Graphics, Computer Perception, Memory and Attention, Computer Software, Computer Vision, Computer-Human Interaction Bachelor Thesis, Master Thesis, Semester Project

Diffusion Models for Full-Body Motion Generation ETH Zurich Sensing, Interaction & Perception Lab The goal of this thesis is to design new methods based on Diffusion models for IMUs-based full-body pose estimation. Computer Graphics, Computer Vision, Intelligent Robotics, Pattern Recognition, Signal Processing, Simulation and Modelling, Virtual Reality and Related Simulation Master Thesis, Semester Project

Computational design of automated factories ETH Zurich Computational robotics laboratory (Prof. Stelian Coros) Industrial robots are revolutionizing traditional logistics and manufacturing machinery, thanks to their flexibility in spatial movements and capabilities for multi-tasking. This shows promises for a new generation of smart factories that can swiftly adapt their layouts and functions to new industrial demands. However, most automated factories today are planned manually, leading to substantial downtime and inflexibility. This project explores the potential of automated robot layout and coordination in a factory environment. We will develop an algorithmic framework that, given a high-level automation goal and hardware budget, generates the factory layout and collaborative plan of the deployed robots. Engineering and Technology, Information, Computing and Communication Sciences Master Thesis, Semester Project

Differentiable Rendering for In-the-Wild Hair Reconstruction ETH Zurich Advanced Interactive Technologies Human hair reconstruction plays a massive role in modern AV/VR and special effects applications. However, existing reconstruction methods rely on expensive structured light capture setups and heuristic data pre-processing to produce detailed, personalized hair models. This project is dedicated to developing differentiable hair rendering methods aimed at achieving robust hair reconstruction from in-the-wild image and video data. Computer Graphics, Computer Vision Master Thesis, Semester Project

Learning to Generate 3D Avatars from 2D Images ETH Zurich Advanced Interactive Technologies Generating 3D humans is a significant and trendy problem in Artificial Intelligence Generated Content(AIGC). This becomes even more popular when a large-scale diffusion model demonstrates its impressive generation ability. We offer projects to develop the SOTA method for 3D human generation. Computer Vision ETH Zurich (ETHZ), IDEA League Student Grant (IDL), Master Thesis, Semester Project

3D Human Modeling and Performance Capture ETH Zurich Advanced Interactive Technologies Digital capture of human bodies is a rapidly growing research area in computer vision and computer graphics that puts scenarios such as life-like mixed-reality (MR) virtual-social interactions into reach. Therefore, we offer projects for modeling and capturing humans at the intersection of computer vision, computer graphics, and machine learning. Computer Graphics, Computer Vision, Virtual Reality and Related Simulation Master Thesis, Semester Project

Developing a virtual reality office workspace ETH Zurich Sensing, Interaction & Perception Lab With the continuous advancements in VR headset hardware, the possibility of creating a virtual-reality office workspace is becoming increasingly feasible. This thesis aims to leverage existing frameworks (e.g., [1,2]) and build upon them to construct an immersive VR office environment that supports users engaged in knowledge work across various real-world settings (office, train, etc.). The student conducting this thesis will integrate existing frameworks available within the SIPLAB to develop a truly immersive experience for a VR workspace. Information, Computing and Communication Sciences Bachelor Thesis, Internship

Personalizing Mixed Reality UIs from User Interactions ETH Zurich Sensing, Interaction & Perception Lab Multi-objective discrete optimization schemes have demonstrated their effectiveness in automatically generating UI layouts for virtual and augmented reality desks [1,2]. However, the quality of the solutions heavily relies on the weighting assigned to different objectives. In this thesis, our objective is to discover an optimal combination of weights that accurately captures the requirements and preferences of an individual user during a single session. To achieve this, we propose incorporating user adjustments of an initially generated UI as feedback to inform the weight updates. By doing so, our aim is to personalize mixed-reality desks with minimal user input, streamlining the customization process. Computer-Human Interaction, Virtual Reality and Related Simulation Bachelor Thesis, ETH Zurich (ETHZ), Master Thesis