2026
Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields
ICLR 2026poster
Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional fields, yet they face a critical fidelity-speed dilemma: deep MLPs suffer from high inference cost, while efficient embed…