Machine Learning

We work on algorithms for finding hidden structure in large data sets, using a combination of probabilistic modeling and deep learning, ranging from social media understanding, text mining, and consumer analytics to visual computing and content generation.

Latest Publications

CANRIG: Cross-Attention Neural Face Rigging with Variable Local Control

VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations

April 4, 2026
Eurographics (2026)

Fatemeh Zargarbashi (ETH Zurich, DisneyResearch|Studios)
Dhruv Agrawal (ETH Zurich, DisneyResearch|Studios)
Jakob Buhmann (DisneyResearch|Studios)
Martin Guay (DisneyResearch|Studios)
Stelian Coroa (ETH Zurich)
Robert Sumner (DisneyResearch|Studios)

Implicit Bézier Motion Model for Precise Spatial and Temporal Control

Synth2Track Editor for Efficient Match-Animation

July 21, 2025
SIGGRAPH (2025)

Jakob Buhmann (DisneyResearch|Studios)
Douglas L. Moore (Industrial Light & Magic)
Dominik Borer (DisneyResearch|Studios)
Martin Guay (DisneyResearch|Studios)

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion

July 16, 2025
SIGGRAPH (2025)

Manuel Kansy (DisneyResearch|Studios/ETH Zurich)
Jacek Naruniec (DisneyResearch|Studios)
Christopher Schroers (DisneyResearch|Studios)
Markus Gross (DisneyResearch|Studios/ETH Zurich)
Romann M. Weber (DisneyResearch|Studios)

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

April 23, 2025
ICLR (2025)

Seyedmorteza Sadat (ETH Zurich)
Otmar Hilliges (ETH Zurich)
Romann M. Weber (DisneyResearch|Studios)

Browse Publications