Presentation
15. Where to Learn Matters: Feature-Aware Sampling for Neural SDF Reconstruction
SessionPosters: 3D & Geometry
DescriptionWe present a simple, plug-and-play two-stage adaptive sampling strategy for neural signed-distance-field reconstruction that reallocates training toward geometrically informative regions, improving frame fidelity, sharp-feature recovery, and overall reconstruction quality on the ABC benchmark without changing the underlying network architecture or reconstruction loss.
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
INVITED TO THE FIRST ROUND OF THE STUDENT RESEARCH COMPETITION
Contributors
Event Type
Poster
TimeSunday, 19 July 20269:00am - 5:30pm PDT
LocationWest Hall Lobby
Session TimeSunday, 19 July 20269:00am - 5:30pm PDTMonday, 20 July 20269:00am - 5:30pm PDTTuesday, 21 July 20269:00am - 5:30pm PDTWednesday, 22 July 20269:00am - 5:30pm PDTThursday, 23 July 20269:00am - 5:30pm PDT
LocationWest Hall Lobby
Full Conference Supporter
Full Conference
Experience
