Presentation
Dictionary Fields: Learning a Neural Basis Decomposition
SessionDeep Geometric Learning
DescriptionDictionary Fields is a novel representation which factorizes a signal into a coefficient and a basis field and exploits periodic transformations to apply the same basis functions across multiple locations and scales. We show that Dictionary Fields lead to improvements in approximation quality, compactness, and training time.
Event Type
Technical Paper
TimeThursday, 10 August 20232:11pm - 2:22pm PDT
LocationRoom 515 A
Research & Education
Livestreamed
Recorded
Modeling
Rendering
FC
FCS
V
VS
EFC