Visual Computing
We strive to improve Disney’s production pipelines and creative processes, expanding the designer’s toolbox in terms of rendering, animation, capture, stylization, interaction, and efficiency. Our technology allows designers to tell their story. We also develop algorithms to better understand our audiences and create new modes of interaction.
Latest Publications
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
December 10, 2024
NeurIPS (2024)
Xiang Zhang (DisneyResearch|Studios/ETH Zurich)
Bingxin Ke (ETH Zurich)
Hayko Riemenschneider (DisneyResearch|Studios)
Nando Metzger (ETH Zurich)
Anton Obukhov (ETH Zurich)
Markus Gross (DisneyResearch|Studios/ETH Zurich)
Konrad Schindler (ETH Zurich)
Christopher Schroers (DisneyResearch|Studios)
Revitalizing Legacy Video Content: Deinterlacing with Bidirectional Information Propagation
November 24, 2024
British Machine Vision Conference (BMVC) (2024)
Zhaowei Gao (DisneyResearch|Studios / ETH Zürich)
Mingyang Song (DisneyResearch|Studios / ETH Zürich)
Christopher Schroers (DisneyResearch|Studios)
Yang Zhang (DisneyResearch|Studios)
Skel-inbetweening for Intuitive Neural Motion Authoring
November 11, 2024
ACM SIGGRAPH Asia (2024)
Dhruv Agrawal (DisneyResearch|Studios/ETH Joint PhD)
Jakcob Buhmann (DisneyResearch|Studios)
Dominik Borer (DisneyResearch|Studios)
Robert W. Sumner (DisneyResearch|Studios/ETH Zurich)
Martin Guay (DisneyResearch|Studios)
RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards
November 4, 2024
Conference on Robot Learning (2024)
Fatemeh Zargarbashi (DisneyResearch|Studios/ETH Joint PhD)
Jin Cheng (ETH Zurich)
Dongho Kang (ETH Zurich)
Robert W. Sumner (DisneyResearch|Studios)
Stelian Coros (ETH Zurich)
Efficient Video Encoder Autotuning via Offline Bayesian Optimization and Supervised Learning
October 1, 2024
International Workshop on Multimedia Signal Processing (2024)
Roberto Azevedo (DisneyResearch|Studios)
Yuanyi Xue (Disney Entertainment/ESPN Tech.)
Xuewei Meng (Disney Entertainment/ESPN Tech.)
Wenhao Zhang (Disney Entertainment/ESPN Tech.)
Scott Labrozzi (Disney Entertainment/ESPN Tech.)
Christopher Schroers (DisneyResearch|Studios)
Lossy Image Compression with Foundation Diffusion Models
September 28, 2024
European Conference on Computer Vision (ECCV) (2024)
Lucas Relic (DisneyResearch|Studios/ETH Zurich)
Roberto Azevedo (DisneyResearch|Studios)
Markus Gross (DisneyResearch|Studios/ETH Zurich)
Christopher Schroers (DisneyResearch|Studios)