Institute for Intelligent Interactive SystemsOpen OpportunitiesWhile camera-based capture systems remain the gold standard for recording human motion, learning-based tracking systems based on sparse wearable sensors are gaining popularity. Most commonly, they use inertial sensors, whose propensity for drift and jitter have so far limited tracking accuracy. Ultra-wideband (UWB) is a radio technology that offers precise ranging capabilities and is integrated into modern smart devices such as iPhones and Apple AirTags. Our recent work, Ultra Inertial Poser, accepted by SIGGRAPH'24, has shown great potential to combine IMU with UWB sensors to constrain drift and jitter in inertial tracking via inter-sensor distances. As we are in the early stages of development, there is still significant room for improvement in the methodology. In this project, we aim to design a deep learning model to improve our dataset's human motion tracking results.
Note: This project will focus on developing a novel supervised learning-based method. We have a clean and synchronized dataset ready (UIP-DB) for training and testing alongside ground-truth tracking data for all joints. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| What optimizations are necessary to make reflective PPG sensors reliably work on tissue with limited blood perfusion?
Note: Candidates should have experience in hardware design (analog circuits, embedded systems, and basic signal processing). - Electrical and Electronic Engineering, Information, Computing and Communication Sciences
- Bachelor Thesis, Master Thesis, Semester Project
| Latent diffusion models (LDMs) [1] have recently emerged as a powerful tool for high-quality image generation, offering superior scalability and training efficiency compared to pixel-space diffusion models. While the network architectures of LDMs have received significant attention, other design aspects of these models (for example the forward noise schedule and the autoencoder) remain underexplored. This project aims to enhance the characteristics of LDMs, e.g., quality and efficiency, by investigating various design elements of latent diffusion models.
- Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| 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
|
|