A wavelet-guided adaptive INR for DEMs achieves 66.25 dB PSNR on Swiss tiles with 3.2x fewer parameters than prior work, plus post-training compression to 1.23 bpp.
Fixed-rate compressed floating-point arrays.IEEE Transactions on Visualization and Computer Graphics, 20(12):2674–2683
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Sketch-based regularization allows in situ training of implicit neural compressors to approximately match offline performance on 2D/3D simulation data at high compression rates.
Introduces a terrain-specific benchmark showing cross-domain gaps in INR methods and demonstrates that HUVR+SIREN achieves superior height and derivative fidelity in a compact quantized format.
ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.
A new high-performance framework combining R-ChFSI, mixed-precision computation, and compressed communication enables exascale fully relativistic pseudopotential DFT calculations for systems up to 100,000 electrons.
FluidViews provides a web-based framework with drag-and-drop token filters and highlight tokens for fluid interaction in heterogeneous multi-view visual analytics.
citing papers explorer
-
ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation
A wavelet-guided adaptive INR for DEMs achieves 66.25 dB PSNR on Swiss tiles with 3.2x fewer parameters than prior work, plus post-training compression to 1.23 bpp.
-
In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
Sketch-based regularization allows in situ training of implicit neural compressors to approximately match offline performance on 2D/3D simulation data at high compression rates.
-
Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data
Introduces a terrain-specific benchmark showing cross-domain gaps in INR methods and demonstrates that HUVR+SIREN achieves superior height and derivative fidelity in a compact quantized format.
-
ANTIC: Adaptive Neural Temporal In-situ Compressor
ANTIC reduces storage for large-scale PDE simulations by orders of magnitude through adaptive temporal snapshot selection combined with continual neural-field residual compression while preserving physics accuracy.
-
Towards exascale fully relativistic pseudopotential density functional theory calculations enabled by mixed-precision computation and compressed-communication using residual based subspace iteration
A new high-performance framework combining R-ChFSI, mixed-precision computation, and compressed communication enables exascale fully relativistic pseudopotential DFT calculations for systems up to 100,000 electrons.
-
FluidViews: Adaptive Drag-and-Drop Token Filters for Heterogeneous Multi-View Visual Analytics
FluidViews provides a web-based framework with drag-and-drop token filters and highlight tokens for fluid interaction in heterogeneous multi-view visual analytics.