Sergio Sancho

I'm a joint PhD student at ETH Zurich and Disney Research, supervised by Markus Gross and Marios Papas. I earned my Master's degree in 2023 from ETH Zurich, and my Bachelor's degree in 2020 from the University of Valencia.

From an early age, I've been fascinated by the technical and creative sides of filmmaking, especially animation. My research focuses on computer graphics, physically-based rendering and simulation, and how these areas connect with machine learning and generative models.

Sergio Sancho

Research

Neural Render Proxies for Interactive and Differentiable Lighting
Neural Render Proxies for Interactive and Differentiable Lighting
Sergio Sancho, Alexander Rath, Marco Manzi, Pascal Chang, Amit Bermano, Derek Nowrouzezahrai, Markus Gross, Marios Papas

We train small, scene-specific neural networks with a decoupled rendering algorithm to enable interactive relighting and art-directed light edits of complex production scenes.

LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping
LookingGlass: Generative Anamorphoses via Laplacian Pyramid Warping
Pascal Chang, Sergio Sancho, Jingwei Tang, Markus Gross, Vinicius Azevedo

We repurpose latent diffusion models to generate high-quality, complex, multi-view optical illusions such as anamorphoses.

The Impulse Particle-In-Cell Method
The Impulse Particle-In-Cell Method
Sergio Sancho, Jingwei Tang, Christopher Batty, Vinicius Azevedo

We propose a hybrid fluid simulation method that uses the impulse formulation on particles to improve vorticity preservation.

ANISE: an application to design mechanobiology simulations of planar epithelia
ANISE: an application to design mechanobiology simulations of planar epithelia
Ángel Rodríguez, Sergio Sancho, Míriam Rodríguez, Miguel Gamón, LÊna Guitou, Rafael Martínez, Javier Buceta

We develop a user-friendly application that simplifies the setup of mechanobiology simulations through a comprehensive graphical interface.

Other Projects

Vorticity-Preserving Methods for Efficient Fluid Simulation
Vorticity-Preserving Methods for Efficient Fluid Simulation
Supervisors: Vinicius Azevedo, Jingwei Tang, Markus Gross

ETH Medal Award

We explore new schemes for fluid simulation in order to improve energy and vorticity preservation capabilities. In particular, we propose novel Eulerian and Lagrangian frameworks based on the vorticity-streamfunction and the impulse formulations.

Computer Graphics Project: Out of Place
Computer Graphics Project: Out of Place
Dario Mylonopoulos, Sergio Sancho

1st Prize Award at ETH Rendering Competition

We implement advanced features on top of an educational physically-based path tracer, such as volumetric rendering with ratio tracking, principled BSDFs and lens-based camera models.

Virtual Reality Training Simulators with Natural Hand Interaction
Virtual Reality Training Simulators with Natural Hand Interaction
Supervisor: Rafael MartĂ­nez

Best Bachelor's Thesis Award

We develop a framework that brings Virtual Reality headsets to existing simulation environments for crane and construction training. We focus on a novel hand-detection interface that lets users operate the machinery with both real and virtual controllers.

Education

Work Experience

Teaching