Presentation
NESI: Neural Explicit-Shape-Intersection-Based Geometry Representation
DescriptionWe introduce NESIs, a compact representation of detailed 3D shapes as intersections of neural explicit height-field surfaces (HFs). NESI provides more accurate approximations of the input than state-of-the-art alternatives with the same parameter count, while efficiently supporting processing operations such as occupancy queries and parametric access.
Event Type
Technical Papers
TimeThursday, 18 December 20251:54pm - 2:05pm HKT
LocationMeeting Room S421, Level 4