Disney Research Studios
  • Research
    • Machine Learning
    • Visual Computing
    • Data Sets
  • Publications
  • People
    • Leadership
    • Research Staff
    • Support Teams
    • Alumni
  • Careers
  • Outreach
  • About Us
Select Page
Deep Adaptive Sampling and Reconstruction using Analytic Distributions

Deep Adaptive Sampling and Reconstruction using Analytic Distributions

by Sarah Frigg | Nov 30, 2022 | Rendering, Video Processing, Visual Computing

Deep Adaptive Sampling and Reconstruction using Analytic Distributions   We propose an adaptive sampling and reconstruction method for offline Monte Carlo rendering. November 30, 2022ACM SIGGRAPH Asia (2022)   Authors Farnood Salehi (DisneyResearch|Studios) Marco...
Contrastive Learning for Controllable Blind Video Restoration

Contrastive Learning for Controllable Blind Video Restoration

by Sarah Frigg | Nov 21, 2022 | Rendering, Video Processing, Visual Computing

Contrastive Learning for Controllable Blind Video Restoration   We demonstrate state of the art results compared to most recent video super-resolution and denoising methods. November 21, 2022British Machine Vision Conference (BMVC) (2022)   Authors Givi Meishvili...
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, Machine Learning, VFX

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...
Automatic Feature Selection for Denoising Volumetric Renderings

Automatic Feature Selection for Denoising Volumetric Renderings

by Sarah Frigg | Sep 19, 2022 | Rendering, Video Processing, Visual Computing

Automatic Feature Selection for Denoising Volumetric Renderings   We propose a method for constructing feature sets that significantly improve the quality of neural denoisers for Monte Carlo renderings with volumetric content. April 7, 2022Eurographics Symposium on...
« Older Entries
Next Entries »
© Copyright DisneyResearch|Studios