3 papers
cs.CV2026
Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data
Haoan Feng, Xin Xu, Leila De Floriani
Implicit neural representations (INRs) model a signal as a continuous coordinate-to-value function. For terrain elevation data, this supports analytic derivatives, arbitrary-resolu…
cs.LG2026
ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation
Haoan Feng, Xin Xu, Leila De Floriani
Digital elevation models (DEMs) underpin terrain analysis in Geographic Information Systems (GIS), but commonly as raster representation, they rely on interpolation for off-grid sa…
cs.CV2026
SASNet: Spatially-Adaptive Sinusoidal Networks for INRs
Haoan Feng, Diana Aldana, Tiago Novello +1
Sinusoidal neural networks (SIRENs) are powerful implicit neural representations (INRs) for low-dimensional signals in vision and graphics. By encoding input coordinates with sinus…