Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Human-centered View Synthesis
In this project, we will propose a pipeline to generate novel view synthesis of multiple human performers. Please email the host for more details of the project.
Keywords: 3D reconstruction, human model, novel view synthesis
Requirements: We are looking for independent and self-motivated students who should have taken a recognized deep learning or a modern computer vision course (e.g., Machine Perception) and should be skilled in Python and PyTorch. The student is encouraged to submit to a top-tier conference (e.g. CVPR).
Some Related Work:
1. VolSDF: https://lioryariv.github.io/volsdf/
2. Multi-Person Pose Estimation: https://ait.ethz.ch/projects/2021/multi-human-pose/
3. NeRF: https://www.matthewtancik.com/nerf
4. SNARF: https://xuchen-ethz.github.io/snarf/
Requirements: We are looking for independent and self-motivated students who should have taken a recognized deep learning or a modern computer vision course (e.g., Machine Perception) and should be skilled in Python and PyTorch. The student is encouraged to submit to a top-tier conference (e.g. CVPR).
Each year the IDEA League offers the students of its partner universities over 180 monthly grants for a short-term research exchange. In general, these grants are awarded based on academic merit. For more information visit http://idealeague.org/student-grant/
Semester Project
Master Thesis
CLS Student Project [managed by Max Planck ETH Center for Learning Systems]