mlsanityData to 14 Oct 2026

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

arXiv 2401.11611 ↗First posted 21 Jan 2024cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Reliably reconstructing physical fields from sparse sensor data is a challenge that frequently arises in many scientific domains. In practice, the process generating the data often is not understood to sufficient accuracy. Therefore, there is a growing interest in using the deep neural network route to address the problem. This work presents a novel approach that learns a continuous representation of the physical field using implicit neural representations (INRs). Specifically, after factorizing spatiotemporal variability into spatial and temporal components using the separation of variables technique, the method learns relevant basis functions from sparsely sampled irregular data points to develop a continuous representation of the data. In experimental evaluations, the proposed model outperforms recent INR methods, offering superior reconstruction quality on simulation data from a state-of-the-art climate model and a second dataset that comprises ultra-high resolution satellite-based sea surface temperature fields.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 26 of its 54 references that are in the map. First posted on arXiv 21 Jan 2024.

Builds on

26 of 54 references.

References · 26

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  7. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  8. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  9. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  10. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  11. 2021Neural Fields in Visual Computing and Beyondcited by 540
  12. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
14 more
  1. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 420
  2. 2018Deep Fluids: A Generative Network for Parameterized Fluid Simulationscited by 121
  3. 2020MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Frameworkcited by 78
  4. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  5. 2021Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fieldscited by 71
  6. 2022Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal datacited by 37
  7. 2019Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomycited by 36
  8. 2022Compressing multidimensional weather and climate data into neural networkscited by 31
  9. 2022Arbitrary-Scale Image Synthesiscited by 20
  10. 2020PDE-Driven Spatiotemporal Disentanglementcited by 19
  11. 2023Learning Vortex Dynamics for Fluid Inference and Predictioncited by 17
  12. 2021SPIN: Simplifying Polar Invariance for Neural networks Application to vision-based irradiance forecastingcited by 7
  13. 2021Faster Kernel Interpolation for Gaussian Processescited by 5
  14. 2017Inferring propagation paths for sparsely observed perturbations on complex networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 8; 2026: 8.

20 papers.

Sort:

By area:

  1. 2024Deep Operator Learning for High-Fidelity Fluid Flow Field Reconstruction from Sparse Sensor Measurementscited by 9
  2. 2025Explorable INR: An Implicit Neural Representation for Ensemble Simulation Enabling Efficient Spatial and Parameter Explorationcited by 8
  3. 2024Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learnercited by 7
  4. 2025Breaking the Discretization Barrier of Continuous Physics Simulation Learningcited by 4
  5. 2026SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Frameworkcited by 2
  6. 2026From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstructioncited by 2
  7. 2024Implicit Neural Representations for Simultaneous Reduction and Continuous Reconstruction of Multi-Altitude Climate Datacited by 1
  8. 2025STACI: Spatio-Temporal Aleatoric Conformal Inferencecited by 1
  9. 2025FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensemblescited by 1
  10. 2026LASER: Learning Active Sensing for Continuum Field Reconstructioncited by 1
  11. 2024Studying the Impact of Latent Representations in Implicit Neural Networks for Scientific Continuous Field Reconstructioncited by 0
  12. 2025Collaborative Imputation of Urban Time Series through Cross-city Meta-learningcited by 0
8 more
  1. 2025Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecastingcited by 0
  2. 2025Dynamical Implicit Neural Representationscited by 0
  3. 2025Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representationcited by 0
  4. 2026Sparsely-Supervised Data Assimilation via Physics-Informed Schr"odinger Bridgecited by 0
  5. 2026WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terraincited by 0
  6. 2026TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensingcited by 0
  7. 2026REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracerscited by 0
  8. 2026Refined Grid Sampling for Efficient Implicit Neural Representations of Large-Scale Scientific Datacited by 0