Scholar
J P Lewis
Google Scholar ID: jGEPl8kAAAAJ
NVIDIA Research and Victoria University
Citations & Impact
Citations
5,690
H-index
28
i10-index
49
Publications
20
Co-authors
24
list available
Contact
No contact links provided.
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- - Publications: Deep Learning without Back-Propagation (arxiv 2019, AAAI 20)
- - Projects: Neural matte extraction without training, Universal Image Generator, Direct Manipulation Blendshapes, Pose Space Deformation (PSD), Texture Space Diffusion (TSD), UCAP dense markerless face capture, Mapping the mental space of game genres, Limits to software estimation, Perceptual segmentation for NPR sketching
Research Experience
- - Neural matte extraction without training
- - Deep Learning without Back-Propagation
- - Universal Image Generator
- - Direct Manipulation Blendshapes
- - VisualIDs: User interfaces need scenery, and suitable scenery can be invented with computer graphics techniques
- - Pose Space Deformation (PSD): A creature skinning/deformation algorithm that combines aspects of skeleton-driven skinning and blendshapes and improves on each
- - Texture Space Diffusion (TSD): An approach to subsurface scattering for skin, developed for the Matrix sequels
- - UCAP dense markerless face capture: Used on Matrix sequels
- - Mapping the mental space of game genres
- - Limits to software estimation
- - Perceptual segmentation for NPR sketching
Background
- Current research interests include applications of statistical learning and computer vision in the arts.
