Disney Research Studios
  • Projects
  • Research
    • Artificial Intelligence
    • Machine Learning
    • Visual Computing
    • Data Sets
  • Publications
  • People
    • Leadership
    • Research Staff
    • Support Teams
    • Alumni
  • Careers
  • Outreach
  • About Us
Select Page
Self-Supervised Effective Resolution Estimation with Adversarial Augmentations

Self-Supervised Effective Resolution Estimation with Adversarial Augmentations

by Sarah Frigg | Jan 3, 2023 | Capture, Digital Humans, Machine Learning

Self-Supervised Effective Resolution Estimation with Adversarial Augmentations   We demonstrate that our method outperforms state-of-the-art image quality assessment methods in estimating the sharpness of real and generated human faces. January 3, 2023 IEEE Winter...
Production-Ready Face Re-Aging for Visual Effects

Production-Ready Face Re-Aging for Visual Effects

by Sarah Frigg | Nov 30, 2022 | Capture, Digital Humans, Machine Learning

Production-Ready Face Re-Aging for Visual Effects   We demonstrate how the simple U-Net, surprisingly, allows us to advance the state of the art for re-aging real faces on video, with unprecedented temporal stability and preservation of facial identity across variable...
TempFormer: Temporally Consistent Transformer for Video Denoising

TempFormer: Temporally Consistent Transformer for Video Denoising

by Sarah Frigg | Oct 11, 2022 | Rendering, Video Processing, Visual Computing

TempFormer: Temporally Consistent Transformer for Video Denoising   We propose an efficient hybrid Transformer-based model, TempFormer, which composes SpatioTemporal Transformer Blocks (STTB) and 3D convolutional layers. October 11, 2022European Conference on Computer...
Learning Dynamic 3D Geometry and Texture for Video Face Swapping

Learning Dynamic 3D Geometry and Texture for Video Face Swapping

by Sarah Frigg | Oct 5, 2022 | Capture, Digital Humans, Machine Learning

Learning Dynamic 3D Geometry and Texture for Video Face Swapping   We approach the problem of face swapping from the perspective of learning simultaneous convolutional facial autoencoders for the source and target identities, using a shared encoder network with...
Facial Animation with Disentangled Identity and Motion using Transformers

Facial Animation with Disentangled Identity and Motion using Transformers

by Sarah Frigg | Sep 13, 2022 | Capture, Digital Humans, Machine Learning

Facial Animation with Disentangled Identity and Motion using Transformers   We propose a 3D+time framework for modeling dynamic sequences of 3D facial shapes, representing realistic non-rigid motion during a performance.  September 13, 2022ACM/Eurographics Symposium...
« Older Entries
© Copyright DisneyResearch|Studios