NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields
Implicit Neural Representations (INRs) have emerged as a powerful paradigm for representing signals such as images, audio, and 3D scenes. However, existing INR frameworks -- including MLPs with Fourier features, SIREN, and multiresolution hash grids -- implicitly assume a \textit{global and stationary} spectral basis. This assumption is fundamentally misaligned with real-world signals whose frequency characteristics vary significantly across space, exhibiting local high-frequency textures, smooth regions, and frequency drift phenomena. We propose \textbf{Neural Spectral Transport Representation (NSTR)}, the first INR framework that \textbf{explicitly models a spatially varying local frequency field}. NSTR introduces a learnable \emph{frequency transport equation}, a PDE that governs how local spectral compositions evolve across space. Given a learnable local spectrum field $S(x)$ and a frequency transport network $F_θ$ enforcing $\nabla S(x) \approx F_θ(x, S(x))$, NSTR reconstructs signals by spatially modulating a compact set of global sinusoidal bases. This formulation enables strong local adaptivity and offers a new level of interpretability via visualizing frequency flows. Experiments on 2D image regression, audio reconstruction, and implicit 3D geometry show that NSTR achieves significantly better accuracy-parameter trade-offs than SIREN, Fourier-feature MLPs, and Instant-NGP. NSTR requires fewer global frequencies, converges faster, and naturally explains signal structure through spectral transport fields. We believe NSTR opens a new direction in INR research by introducing explicit modeling of space-varying spectrum.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Self-supervised Contrastive Learning for Cross-domain Hyperspectral Image Representation
Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervis…
Contrastive LearningSelf-Supervised LearningTransfer LearningUnbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering
Hyperspectral images capture vast amounts of high-dimensional spectral information about a scene, making labeling an intensive task that is resistant to out-of-the-box statistical methods. Unsupervised learning of cluste…
Image ClusteringSpectral-transport stability and benign overfitting for minimum norm interpolation
Benign overfitting describes the ability of minimum norm interpolating estimators to generalize despite fitting noisy data exactly. Existing characterizations depend on delicate spectral functionals of the population cov…
The Score Hamiltonian: Mapping Diffusion Models to Adiabatic Transport
We exhibit an exact correspondence between sampling with score-based diffusion models and adiabatic transport of ground states for a family of Schrödinger operators we call Score Hamiltonians, built from the learned scor…
Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans
Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain alignment, such…
Unsupervised Domain AdaptationMusic Genre Recognition