SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces

ArXi:2604.25936v1 Announce Type: cross Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that implicit representations require progressively lower accuracy as query points move farther from the target surface, and that even within the same iso-surface, representation difficulty varies spatially with local geometric complexity.