Presentation

fVDB : A Deep-learning Framework for Sparse, Large Scale, and High Performance Spatial Intelligence
DescriptionWe introduce fVDB, a GPU-optimized framework for deep learning on large-scale 3D data that efficiently accommodates spatial sparsity, based on a novel VDB index grid structure. Our framework is fully integrated with PyTorch and includes a comprehensive collection of operators for tasks such as convolution, pooling, attention, and raytracing.
Event Type
Technical Paper
TimeThursday, 1 August 20249:00am - 9:10am MDT
LocationMile High 2A
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Thursday, 1 August 20249:00am - 10:30am 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
Thursday