Skip to content

Recent Progress of Implicit Neural Representations: Architectural Improvements and Cross-domain Applications

License

Notifications You must be signed in to change notification settings

liuzhen0212/Recent-Progress-of-INR

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

Recent Progress of Implicit Neural Representations:
Architectural Improvements and Cross-domain Applicationss


This repository collects recent advances in the field of Implicit Neural Representations (INR) along with a curated paper list. We have organized these papers into five main categories:

  • Theoretical Understanding
  • Architectural Improvement
  • Data Representation
  • Capability Exploration
  • Downstream Applications We are committed to keeping this repository updated to the best of our ability. Feel free to submit pull requests to contribute to this collection!

If you find this repository useful for your research, we welcome you to follow our work and consider citing our previous publications:

  • (CVPR'25) EVOS: Efficient Implicit Neural Training via EVOlutionary Selector [paper] [code]
  • (AAAI'25) Enhancing Implicit Neural Representations via Symmetric Power Transformation [paper] [code]

News

  • [2025.03.21] Repository Initialization.

Links

Paper list

Table of Content - [Recent Publications](#recent-publications) - [Survey, Benchmark and Important Papers](#survey-benchmark-and-important-papers) - Topical Organization - [Theoretical Understanding](#theoretical-understanding) - [Architectural Improvement](#architectural-improvement) - [Data Representation](#data-representation) - [Capability Exploration](#capability-exploration) - [Downstream Applications](#downstream-applications)

Paper list

Table of Content - [Recent Publications](#recent-publications) - [Survey, Benchmark and Important Papers](#survey-benchmark-and-important-papers) - Topical Organization - [Theoretical Understanding](#theoretical-understanding) - [Architectural Improvement](#architectural-improvement) - [Data Representation](#data-representation) - [Capability Exploration](#capability-exploration) - [Downstream Applications](#downstream-applications)

Recent Publications

CVPR 2025
  • Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
  • STINR: Deciphering Spatial Transcriptomics via Implicit Neural Representation
  • End-to-End Implicit Neural Representations for Classification

  • MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation

  • VI3NR: Variance Informed Initialization for Implicit Neural Representations

  • MIRE: Matched Implicit Neural Representations

  • SINR: Sparsity Driven Compressed Implicit Neural Representations
  • ALIEN: Implicit Neural Representations for Human Motion Prediction under Arbitrary Latency
  • Bias for Action: Video Implicit Neural Representations with Bias Modulation
    [paper] [website]
  • EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
    [paper] [website]
  • STINR: Deciphering Spatial Transcriptomics via Implicit Neural Representation
  • MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation
  • HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks
  • Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks
  • Blind-Spot Real-world Image Denoising via Implicit Neural Pixel Resampling
  • Few-shot Implicit Function Generation via Equivariance
    [paper]
ICLR 2025
  • Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation
    [paper] [code]
  • PIN: Prolate Spheroidal Wave Function-based Implicit Neural Representations
    [paper]
  • No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
    [paper]
  • Isometric Regularization for Manifolds of Functional Data
    [paper] [website]
  • FreSh: Frequency Shifting for Accelerated Neural Representation Learning
    [paper] [code] [website]
  • Fast Training of Sinusoidal Neural Fields via Scaling Initialization
    [paper]
  • Meta-Continual Learning of Neural Fields
    [paper] [code]
  • Grounding Continuous Representations in Geometry: Equivariant Neural Fields
    [paper] [code]
  • Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields
    [paper]
  • GridMix: Exploring Spatial Modulation for Neural Fields in PDE Modeling
    [paper] [code]
  • Distilling Dataset into Neural Field
    [paper] [code]
AAAI 2025
  • Sharpening Neural Implicit Functions with Frequency Consolidation Priors
    [paper] [code]
  • Sparis: Neural Implicit Surface Reconstruction of Indoor Scenes from Sparse Views [paper]
  • Enhancing Implicit Neural Representations via Symmetric Power Transformation
    [paper] [code]
  • Unsupervised Self-prior Embedding Implicit Neural Representation for Iterative Sparse-View CT Reconstruction
    [paper] [code]
  • Adaptive Wavelet-Positional Encoding for High-Frequency Information Learning in Implicit Neural Representation
NeurIPS 2024
  • NVRC:Neural Video Representation Compression
    [paper]
  • Learning Transferable Features for Implicit Neural Representations
    [paper] [website]
  • Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
    [paper] [code] [website]
  • Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
    [paper] [code] [website]
  • Neural Experts: Mixture of Experts for Implicit Neural Representations
    [paper] [code]
  • Towards Croppable Implicit Neural Representations
    [paper] [code]
  • HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
    [paper] [code]
  • Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation
    [paper] [code]
  • Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation
    [paper]
  • Score-based 3D molecule generation with neural fields
    [paper]
ECCV 2024
  • Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
    [paper] [code]
  • UNIKD: UNcertainty-filtered Incremental Knowledge Distillation for Neural Implicit Representation
    [paper] [code]
  • Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution
    [paper] [code]
  • Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics
    [paper] [code]
  • Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data
    [paper] [code]
  • SAIR: Learning Semantic-aware Implicit Representation
    [paper] [code]
  • NeRMo: Learning Implicit Neural Representations for 3D Human Motion Prediction
    [paper] [code]
  • Fast Encoding and Decoding for Implicit Video Representation
    [paper] [code] [website]
MM 2024
  • QS-NeRV: Real-Time Quality-Scalable Decoding with Neural Representation for Videos
    [paper]
  • Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation
    [paper]
  • HINER: Neural Representation for Hyperspectral Image
    [paper]
ICML 2024
  • A sampling theory perspective on activations for implicit neural representations
    [paper]
  • ReLUs Are Sufficient for Learning Implicit Neural Representations
    [paper] [code]
  • Nonparametric Teaching of Implicit Neural Representations
    [paper] [website]
  • Quantum Implicit Neural Representations
    [paper]
  • Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries
    [paper]

CVPR 2024
ICLR 2024
  • Graph Neural Networks for Learning Equivariant Representations of Neural Networks
    [paper] [code]

Survey, Benchmark and Important Papers


Survey

(ICCV'2023) Implicit Neural Representation in Medical Imaging: A Comparative Survey
[paper] [code]

Datasets & Benchmark

(ICML'2022) From data to functa: Your data point is a function and you can treat it like one
[paper] [code]

(NeurIPS'2024) Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scene
[paper] [code]

(CVPR'2024) How to Train Neural Field Representations: A Comprehensive Study and Benchmark
[paper] [code] [website]

Important Papers

(NeurIPS'2020) (SIREN) Implicit Neural Representations with Periodic Activation Functions
[paper] [code]

(ECCV'2020) NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
[paper] [code][website]

Theoretical Understanding

Architectural Improvement

Basic Architecture & Activation Functions

(NeurIPS'2020) (Position Encoding) Fourier features let networks learn high frequency functions in low dimensional domains
[paper] [code]

(NeurIPS'2020) (SIREN) Implicit Neural Representations with Periodic Activation Functions
[paper] [code]

(ICLR'2021) (MFN) Multiplicative Filter Networks
[paper] [code]

(ECCV'2022) (GAUSS) Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate MLPs
[paper]

(CVPR'2023) (WIRE) Wavelet Implicit Neural Representations
[paper] [code]

(CVPR'2024) FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functions
[paper] [code]

(ICML'2024) ReLUs Are Sufficient for Learning Implicit Neural Representations
[paper] [code]

Initialization

(CVPR'2021) Learned initializations for optimizing coordinate-based neural representations
[paper] [code]

(ECCV 2022) Transformers as Meta-learners for Implicit Neural Representation
[paper] [code]

(ICLR 2025) Fast Training of Sinusoidal Neural Fields via Scaling Initialization
[paper]

Auxiliary Network

(ICCV 2021) Modulated Periodic Activations for Generalizable Local Functional Representations
[paper] [website]

(WACV 2025) INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings
[paper] [code] [website]

Partition-based Acceleration

(TOG 2021) ACORN: Adaptive coordinate networks for neural representation
[paper][code][website]

Sampling

(CVPR 2024) Accelerating Neural Field Training via Soft Mining
[paper][code][website]

(ICML 2024) Nonparametric Teaching of Implicit Neural Representations
[paper][code][website]

(CVPR 2025) EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
[paper] [code]

Data Transformation

(CVPR 2023) DINER: Disorder-Invariant Implicit Neural Representation
[paper][code][website]

(CVPR 2024) In Search of a Data Transformation That Accelerates Neural Field Training
[paper][code]

(CVPR 2024) Batch Normalization Alleviates the Spectral Bias in Coordinate Networks
[paper][code]

(AAAI 2025) Enhancing Implicit Neural Representations via Symmetric Power Transformation
[paper] [code]

Level Of Details

Regularization

Alternatives

Data Representation

Time Series

Audio

Video

Shape

Radiance Field

Alternatives

Capability Exploration

Neural Functional & Functa

(ICML'2022) From data to functa: Your data point is a function and you can treat it like one
[paper] [code]

(NeurIPS'2023) Permutation Equivariant Neural Functionals
[paper] [code]

(NeurIPS'2023) Neural Functional Transformers
[paper] [code]

(ICLR'2024) Graph Neural Networks for Learning Equivariant Representations of Neural Networks
[paper] [code]

Implicit Editing

(NeurIPS'2024) Towards Croppable Implicit Neural Representations
[paper] [code] [website]

Explanation & Visualization

(CVPR'2024) Explaining the Implicit Neural Canvas: Connecting Pixels to Neurons by Tracing their Contributions
[paper] [code] [website]

Downstream Applications

Compression

Image Enhancement

(CVPR'2024) Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
[paper] [code]

(NeurIPS'2024) Cross-Scale Self-Supervised Blind Image Deblurring via Implicit Neural Representation
[paper] [code]

(ECCV'2024) Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
[paper] [code]

Generation

(CVPR'2023) Implicit Diffusion Models for Continuous Super-Resolution
[paper] [code]

(ICLR'2024) DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
[paper] [code]

(NeurIPS'2024) Score-based 3D Molecule Generation with Neural Fields
[paper]

(CVPR'2024) Image Neural Field Diffusion Models
[paper] [code]

(CVPR'2025) Few-shot Implicit Function Generation via Equivariance
[paper]

Anomaly Detection

(KDD'2025) TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection
[paper] [code]

About

Recent Progress of Implicit Neural Representations: Architectural Improvements and Cross-domain Applications

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published