Presentation

NeAT: Neural Adaptive Tomography
SessionRoundtable Session: Neural Objects, Materials and Illumination
Authors
Darius Rückert
Rui Li
Yuanhao Wang
Ramzi Idoughi
Wolfgang Heidrich
Event Type
Technical Paper
Keywords
Rendering
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Recordings
This session WILL NOT be recorded.
TimeMonday, 8 August 202210:45am - 10:53am PDT
LocationEast Building, Ballroom A/B
DescriptionNeural Adaptive Tomography (NeAT) is a hierarchical neural rendering pipeline for inverse rendering tomography. NeAT outperforms the quality of existing optimization-based and neural-rendering-based tomography solvers while being substantially faster.
Authors
Darius Rückert
University of Erlangen-Nuremberg
King Abdullah University of Science and Technology (KAUST)
Rui Li
King Abdullah University of Science and Technology (KAUST)
Yuanhao Wang
King Abdullah University of Science and Technology (KAUST)
Ramzi Idoughi
King Abdullah University of Science and Technology (KAUST)
Wolfgang Heidrich
King Abdullah University of Science and Technology (KAUST)