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
Shape Transformers: Topology-Independent 3D Shape Models Using Transformers

Shape Transformers: Topology-Independent 3D Shape Models Using Transformers

by Martina Megaro | Apr 25, 2022 | Capture, Digital Humans, Machine Learning

Shape Transformers: Topology-Independent 3D Shape Models Using Transformers   We present a new nonlinear parametric 3D shape model based on transformer architectures. April 25, 2022Eurographics 2022   Authors Prashanth Chandran (DisneyResearch|Studios/ETH Joint...
Improved Lighting Models for Facial Appearance Capture

Improved Lighting Models for Facial Appearance Capture

by Martina Megaro | Apr 25, 2022 | Capture, Digital Humans, Machine Learning

Improved Lighting Models for Facial Appearance Capture   We compare the results obtained with a state-of-the-art appearance capture method [RGB∗20], with and without our proposed improvements to the lighting model. April 25, 2022Eurographics 2022   Authors...
Rendering with Style: Combining Traditional and Neural Approaches for High-Quality Face Rendering

Rendering with Style: Combining Traditional and Neural Approaches for High-Quality Face Rendering

by Martina Megaro | Nov 30, 2021 | Capture, Digital Humans, Machine Learning

Rendering with Style: Combining Traditional and Neural Approaches for High-Quality Face Rendering   We propose to combine incomplete, high-quality renderings showing only facial skin with recent methods for neural rendering of faces, in order to automatically and...
Deep Compositional Denoising for High-quality Monte Carlo Rendering

Deep Compositional Denoising for High-quality Monte Carlo Rendering

by Martina Megaro | Jul 30, 2021 | Rendering, Visual Computing

Deep Compositional Denoising for High-quality Monte Carlo Rendering   We propose a deep-learning method for automatically decomposing noisy Monte Carlo renderings into components that kernel-predicting denoisers can denoise more effectively. June 29, 2021Eurographics...
Adaptive Convolutions for Structure-Aware Style Transfer

Adaptive Convolutions for Structure-Aware Style Transfer

by Martina Megaro | Jun 19, 2021 | Capture, Digital Humans, Machine Learning

Adaptive Convolutions for Structure-Aware Style Transfer   We propose Adaptive convolutions; a generic extension of AdaIN, which allows for the simultaneous transfer of both statistical and structural styles in real time. June 19, 2021IEEE Conference on Computer...
« Older Entries
© Copyright DisneyResearch|Studios