Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields
About
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 embedding-based models lack sufficient expressiveness. To resolve this, we propose the Decoupled Representation Refinement (DRR) architectural paradigm. DRR leverages a deep refiner network, alongside non-parametric transformations, in a one-time offline process to encode rich representations into a compact and efficient embedding structure. This approach decouples slow neural networks with high representational capacity from the fast inference path. We introduce DRR-Net, a simple network that validates this paradigm, and a novel data augmentation strategy, Variational Pairs (VP) for improving INRs under complex tasks like high-dimensional surrogate modeling. Experiments on several ensemble simulation datasets demonstrate that our approach achieves state-of-the-art fidelity, while being up to 27$\times$ faster at inference than high-fidelity baselines and remaining competitive with the fastest models. The DRR paradigm offers an effective strategy for building powerful and practical neural field surrogates and \rev{INRs in broader applications}, with a minimal compromise between speed and quality.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Conditional Generalization | Nyx (test) | Relative L2 Error0.0318 | 4 | |
| Conditional Generalization | Cloverleaf3D (test) | Relative L2 Error0.0981 | 4 | |
| Conditional Generalization | Nyx low-resolution (x2 reduced) (Unseen Fields) | Rel L2 Error0.0111 | 4 | |
| Conditional Generalization | Nyx Trained Fields low-resolution (x2 reduced) | Relative L2 Error0.0115 | 4 | |
| Conditional Generalization | Cloverleaf3D low-resolution (x2 reduced) (Unseen Fields) | Rel L2 Error0.0938 | 4 | |
| Conditional Generalization | Cloverleaf3D low-resolution (x2 reduced) (train) | Relative L2 Error0.0596 | 4 | |
| Super-Resolution | Nyx Unseen Fields (test) | Relative L2 Loss0.0431 | 4 | |
| Super-Resolution | Nyx Trained Fields (train) | Rel L20.0707 | 4 | |
| Super-Resolution | Cloverleaf3D Unseen Fields (test) | Rel L2 Error0.101 | 4 | |
| Super-Resolution | Cloverleaf3D Trained Fields (train) | Rel L20.087 | 4 |