Presentation

NeuralTO: Neural Reconstruction and View Synthesis of Translucent Objects
DescriptionWe introduce a novel, two-stages framework, which is geared toward high-fidelity surface reconstruction and the novel-view synthesis of translucent objects. In our framework, we propose a theoretical model for the neural radiance field of translucent objects, which parametrizes the density field using a constant extinction coefficient.
Event Type
Technical Paper
TimeMonday, 29 July 20242:30pm - 2:40pm MDT
LocationMile High 2A
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20242:00pm - 3:30pm MDTMile High 2A
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Geometry
Modeling
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday