Disney Research Studios
  • Research
    • Machine Learning
    • Visual Computing
    • Data Sets
  • Publications
  • People
    • Leadership
    • Research Staff
    • Support Teams
    • Alumni
  • Careers
  • Outreach
  • About Us
Select Page
ReBaIR: Reference-Based Image Restoration

ReBaIR: Reference-Based Image Restoration

by America Ortiz | Sep 29, 2025 | Video Processing, Visual Computing

ReBaIR: Reference-Based Image Restoration In this work, we propose a novel and generic reference-based restoration method that is applicable to any model and any task. We start with the observation that restoration models typically operate in feature space before a...
Spline Deformation Field

Spline Deformation Field

by America Ortiz | Aug 26, 2025 | Rendering, Video Processing, Visual Computing

Spline Deformation Field In this paper, we propose a spline-based trajectory representation, where the number of knots explicitly determines the degrees of freedom. This approach enables efficient analytical derivation of velocities, preserving spatial coherence and...
Synth2Track Editor for Efficient Match-Animation

Synth2Track Editor for Efficient Match-Animation

by America Ortiz | Jul 21, 2025 | Capture, Machine Learning, VFX

Synth2Track Editor for Efficient Match-Animation In this work, we developed new tools that significantly reduces the time required for complex shots, combining automation with human expertise to overcome the limitations of current markerless motion capture systems....
Controllable Tracking-Based Video Frame Interpolation

Controllable Tracking-Based Video Frame Interpolation

by America Ortiz | Jul 17, 2025 | Video Processing, Visual Computing

Controllable Tracking-Based Video Frame Interpolation In this work, we address the less explored problem of user-assisted frame interpolation to improve quality and enable control over the appearance and motion of interpolated frames. To this end, we introduce a...
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion

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

by America Ortiz | Jul 16, 2025 | Machine Learning, Video Processing, Visual Computing

Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion In this work, we propose motion-textual inversion, a general method to transfer the semantic motion of a given reference motion video to given target images. It generalizes across various...
« Older Entries
© Copyright DisneyResearch|Studios