Marcel C. Buehler

I conducted my PhD in the Advanced Interactive Technologies lab of the Institute for Intelligent Interactive Systems at ETH Zurich, supervised by Prof. Otmar Hilliges, Dr. Thabo Beeler, and Prof. Markus Gross. In August 2025, I defended my PhD thesis titled Faithful 3D Avatars for Everyone: Prior-Guided Face Reconstruction for High-Quality Novel View Synthesis from Casual Few-Shot Captures to an international committee with Prof. Markus Gross (ETH Zurich), Dr. Thabo Beeler (Google), Prof. Fernando De la Torre (Carnegie Mellon University) and Prof. Gordon Wetzstein (Stanford University).

From May 2024 to June 2025, I conducted research as intern at Nvidia's Data-Driven AI for Robotics group. From July 2022 to May 2024, I was a Student Researcher at Google AR/VR. I obtained my Master's degree in Data Science from ETH Zurich in 2020 and my Bachelor's degree in Computer Science from University of Zurich in 2017.

My research enables to reconstruct personalized, high-quality 3D avatars from just a few smartphone photos. 3D avatar reconstruction from sparse inputs requires resolving fundamental ambiguities. Inspired by how humans use prior knowledge, I research how statistical and neural priors can be injected into neural models to facilitate high-quality, faithful reconstructions. Specifically, I develop neural models of 3D avatars trained on large-scale real and synthetic datasets for novel view synthesis up to 4K resolution. These models enable important applications for AR/VR like telepresence, entertainment, and fashion.

Keywords: 3D avatars; sparse inputs; generative models; differentiable rendering; NeRF; 3D Gaussian Splatting; disentanglement.