Research
Refined Grid Sampling for Efficient Implicit Neural Representations of Large-Scale Scientific Data
arXiv:2610.14205v1 Announce Type: new Abstract: Implicit neural representations (INRs) offer a powerful framework for modeling high-dimensional physical fields, but their training remains inefficient
arXiv:2610.14205v1 Announce Type: new Abstract: Implicit neural representations (INRs) offer a powerful framework for modeling high-dimensional physical fields, but their training remains inefficient because evaluating dense coordinate grids is computationally expensive. Existing coordinate-pruning strategies rely on local error functions that can oversample correlated points and incur substantial overhead from full-grid error evaluation. We introduce Refined Grid Sampling (RGS), which combines stratified grid sampling, error-based refinement, and dynamic grid-resolution adjustment. This design reduces spatial redundancy without evaluating errors over the full grid. On high-resolution Navier--Stokes fields, RGS achieves higher reconstruction accuracy within a fixed wall-clock budget and reaches the accuracy of full-grid training up to 6imes faster than the evaluated baselines.
Related
- Fast Amortized Fitting of Scientific Signals Across Time and Ensembles via Transferable Neural Fields
- ANTIC: Adaptive Neural Temporal In-situ Compressor
- DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Rendering
- A Unified Framework for Structured Flow Modeling: From Continuous Fields to Data-Driven Representations
- In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
Source: arXiv cs.LG | 2026-10-14