REVIEW 6 cited by
Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Implicit Neural Representations (INRs) have emerged as a paradigm in knowledge representation, offering exceptional flexibility and performance across a diverse range of applications. INRs leverage multilayer perceptrons (MLPs) to model data as continuous implicit functions, providing critical advantages such as resolution independence, memory efficiency, and generalisation beyond discretised data structures. Their ability to solve complex inverse problems makes them particularly effective for tasks including audio reconstruction, image representation, 3D object reconstruction, and high-dimensional data synthesis. This survey provides a comprehensive review of state-of-the-art INR methods, introducing a clear taxonomy that categorises them into four key areas: activation functions, position encoding, combined strategies, and network structure optimisation. We rigorously analyse their critical properties, such as full differentiability, smoothness, compactness, and adaptability to varying resolutions while also examining their strengths and limitations in addressing locality biases and capturing fine details. Our experimental comparison offers new insights into the trade-offs between different approaches, showcasing the capabilities and challenges of the latest INR techniques across various tasks. In addition to identifying areas where current methods excel, we highlight key limitations and potential avenues for improvement, such as developing more expressive activation functions, enhancing positional encoding mechanisms, and improving scalability for complex, high-dimensional data. This survey serves as a roadmap for researchers, offering practical guidance for future exploration in the field of INRs. We aim to foster new methodologies by outlining promising research directions for INRs and applications.
Forward citations
Cited by 6 Pith papers
-
PRIME-SVR: Physics-infoRmed Implicit Multi-Echo Slice-to-Volume Reconstruction for Fetal T2 mapping
A self-supervised, physics-regularized neural reconstruction produces high-resolution fetal brain T2 maps at 0.55 T and 1.5 T from multi-echo MRI, with reduced acquisition time.
-
Weight Space Representation Learning via Neural Field Adaptation
Multiplicative LoRA weights of pre-trained neural fields form structured, semantically meaningful representations that outperform prior weight-space methods for generation and classification.
-
Multi-resolution Enhancement for Full Spectrum Neural Representations
A wavelet-based multi-scale neural network with a local kernel enhancement module achieves better rate-distortion on scientific datasets than standard implicit neural representations.
-
Physics-Guided Dual Implicit Neural Representations for Source Separation
A dual implicit neural network with a physics-guided convolution kernel separates single-magnon signals from heterogeneous background in 4D neutron scattering data without labels.
-
Sampling Theory for Super-Resolution with Implicit Neural Representations
For shallow ReLU implicit neural representations with Fourier features, O(K^d) low-pass samples suffice for width-1 recovery and O(s^2) samples for width-s recovery in 2D, using generalized weight decay.
-
Grids Often Outperform Implicit Neural Representations at Compressing Dense Signals
Simple interpolated grids beat tested INRs at equal parameter count on dense 2D and 3D signals, while INRs retain an edge on sparse, lower-dimensional signals.
Discussion (0). Sign in to comment.