Institute for Intelligent Interactive SystemsOpen OpportunitiesCreating 3D human avatars is essential for applications like 3D games, animations, and Metaverse, yet it also requires specific knowledge and significant manual efforts. With the recent advances in 3D generative modeling, various 3D assets can be randomly generated from the models trained with either 2D or 3D data. The tasks for this project include leveraging diffusion models for reconstructing a 3D human avatar from images.
- Computer Graphics, Computer Vision, Virtual Reality and Related Simulation
- ETH Zurich (ETHZ), Lab Practice, Master Thesis, Semester Project
| In civil engineering applications, concrete plates and shells are vital modelling elements for a diverse range of applications such as bridge decks and floor slabs. In order to implement python-based ML algorithms within existing state-of-the-art finite element solvers, a novel communication system is required. The goal of this novel system is creating an interoperability between the old programming language Fortran 77 (of the FE solver) and python (of modern machine learning libraries). - Civil Engineering, Computer Communications Networks
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| In this one—to two-month paid summer research project, we aim to deploy a long-horizon assembly plan to one or several mobile robots in the real world so that a large structure can be built with precision. We will use a motion capture system for localization and object tracking and focus on integrating the tracking system, planning, and control so that the robot can adjust to the tracking inputs to ensure accuracy. - Construction Engineering, Manufacturing Engineering, Mechanical Engineering
- ETH Zurich (ETHZ), Internship, Lab Practice, Student Assistant / HiWi
| 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 humans are a very popular and fast-growing area with manifold applications in AR/VR. However, the dynamic of the existing head avatars is mostly limited to the facial region. In this project, we will focus on realistically rendered avatars that would include realistic modeling of both faces and hair with physically accurate dynamics and interactions. - Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| Estimating human poses within global trajectories is critical for applications such as augmented reality and sports analytics, yet it often demands precisely calibrated cameras and significant computational efforts. With advancements in deep learning and pose estimation technologies, various models can be trained using 2D or 3D motion data. However, effectively integrating these models to predict and analyze human movement trajectories in a continuous and dynamic environment remains challenging. This project aims to create a robust system that estimates and predicts human poses accurately, facilitating advancements in dynamic pose analysis and real-world applications. - Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Lab Practice, Master Thesis, Semester Project
|
|