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

Interactive Generative Motion Editing via Scheduled Inpainting

Two2Four: Generative Quadruped Puppeteering from Human Motion

July 30, 2026
arXiv (2026)

Fatemeh Zargarbashi (DisneyResearch|Studios/ETH Zurich)
Zehong Qiu (DisneyResearch|Studios)
Dhruv Agrawal (DisneyResearch|Studios/ETH Zurich)
Stelian Coros (ETH Zurich)
Robert W. Sumner (DisneyResearch|Studios/ETH Zurich)
Martin Guay (DisneyResearch|Studios)
Jakob Buhmann (DisneyResearch|Studios)

SmoothMotionVectors: Optimizing Your Content for Video Codecs in Free View Video Compression

July 16, 2026
SIGGRAPH (2026)

Mingyang Song (DisneyResearch|Studios/ETH Zurich)
Yang Zhang (DisneyResearch|Studios)
Siyu Tang (ETH Zurich)
Tunç Ozan Aydin (DisneyResearch|Studios)

2D Gaussian Splatting for Bézier Spline Line Art Vectorization

July 16, 2026
SIGGRAPH (2026)

Tianhao Chen (DisneyResearch|Studios/ETH Zurich)
Clara Fernandez (DisneyResearch|Studios)
Marteinn Oskarsson (Walt Disney Animation Studios)
Chuck Tappan (Walt Disney Animation Studios)
Olga Sorkine-Hornung (ETH Zurich)
Markus Gross (DisneyResearch|Studios/ETH Zurich)
Christopher Schroers (DisneyResearch|Studios)
Abdelaziz Djelouah (DisneyResearch|Studios)

Ragged Neighborhood Attention for Spatiotemporal Neural Denoising of Deep Monte Carlo Renderings

A Generative Motion Rig for Artist-Driven Motion Authoring

Browse Publications