Disney Research Studios
  • Research
    • Machine Learning
    • Visual Computing
    • Data Sets
  • Publications
  • People
    • Leadership
    • Research Staff
    • Support Teams
    • Alumni
  • Careers
  • Outreach
  • About Us
Select Page
QUADify: Extracting Meshes with Pixel-level Details and Materials from Images

QUADify: Extracting Meshes with Pixel-level Details and Materials from Images

by America Ortiz | Jun 5, 2024 | Video Processing, Visual Computing

QUADify: Extracting Meshes with Pixel-level Details and Materials from Images In this work, we propose a method to extract regular quad-dominant meshes from posed images. More specifically, we generate a high-quality 3D model through de- composition into an easily...
Artist-Friendly Relightable and Animatable Neural Heads

Artist-Friendly Relightable and Animatable Neural Heads

by America Ortiz | Jun 3, 2024 | Capture, VFX

Artist-Friendly Relightable and Animatable Neural Heads In this work, we simultaneously tackle both the motion and illumination problem, proposing a new method for relightable and animatable neural heads. June 3, 2024CVPR (2024)   Authors Yingyan Xu...
The Impulse Particle-In-Cell Method

The Impulse Particle-In-Cell Method

by America Ortiz | Apr 25, 2024 | Animation, Visual Computing

The Impulse Particle-In-Cell Method In this work, we propose the Impulse Particle-In-Cell (IPIC) method, a novel extension of the popular Affine Particle-In-Cell (APIC) method that makes use of the impulse gauge formulation of the fluid equations. Our approach...
CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields

CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields

by America Ortiz | Mar 18, 2024 | Video Processing, Visual Computing

CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields In this paper, we introduce Controllable Artistic Radiance Fields (CoARF), a novel algorithm for controllable 3D scene stylization. CoARF enables style transfer for specified objects, compositional 3D...
Trajectory Augmentation for Robust Neural Locomotion Controllers

Trajectory Augmentation for Robust Neural Locomotion Controllers

by America Ortiz | Feb 5, 2024 | Animation, Visual Computing

Trajectory Augmentation for Robust Neural Locomotion Controllers In this work, we introduce Trajectory Augmentation (TrajAug), a fully automatic data augmentation technique that generates synthetic motion data by using motion matching to stitch sequences from the...
« Older Entries
Next Entries »
© Copyright DisneyResearch|Studios