JA-SIREN derives deterministic weights for two-layer sinusoidal MLPs via DST and Jacobi-Anger expansion to match target spectra, yielding 67.18 dB PSNR on Kodak with zero variance.
Where do we stand with implicit neural representations? a technical and performance survey
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
years
2026 7representative citing papers
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
A spatially varying filter parameter α(x) lets Fourier-encoded implicit neural representations adapt their frequency response locally, improving reconstruction quality and convergence speed on non-stationary signals.
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
FDINR decomposes RGB-NIR pairs into frequency components via wavelets and employs dual-branch INR with cross-modal supervision and adaptive uncertainty loss to restore low-light images while enabling arbitrary-resolution output.
LIANet encodes multi-temporal Earth observation data into a coordinate-based neural field that supports label-only fine-tuning for downstream tasks without access to raw imagery.
citing papers explorer
-
JA-SIREN: Deterministic Initialization for Sinusoidal Networks via Spectral Matching
JA-SIREN derives deterministic weights for two-layer sinusoidal MLPs via DST and Jacobi-Anger expansion to match target spectra, yielding 67.18 dB PSNR on Kodak with zero variance.
-
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
-
Adaptive Local Frequency Filtering for Fourier-Encoded Implicit Neural Representations
A spatially varying filter parameter α(x) lets Fourier-encoded implicit neural representations adapt their frequency response locally, improving reconstruction quality and convergence speed on non-stationary signals.
-
AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting
AIR amortizes 2D Gaussian splatting into a self-supervised feed-forward network via residual stages, explicit stage control, and Predict-Optimize-Distill training.
-
Frequency-Decomposed INR for NIR-Assisted Low-Light RGB Image Denoising
FDINR decomposes RGB-NIR pairs into frequency components via wavelets and employs dual-branch INR with cross-modal supervision and adaptive uncertainty loss to restore low-light images while enabling arbitrary-resolution output.
-
Location Is All You Need: Continuous Spatiotemporal Neural Representations of Earth Observation Data
LIANet encodes multi-temporal Earth observation data into a coordinate-based neural field that supports label-only fine-tuning for downstream tasks without access to raw imagery.
- ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation