mlsanityData to 14 Oct 2026

NOIR: Neural Operator mapping for Implicit Representations

arXiv 2603.13118 ↗First posted 13 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper presents NOIR, a framework that reframes core medical imaging tasks as operator learning between continuous function spaces, challenging the prevailing paradigm of discrete grid-based deep learning. Instead of operating on fixed pixel or voxel grids, NOIR embeds discrete medical signals into shared Implicit Neural Representations and learns a Neural Operator that maps between their latent modulations, enabling resolution-independent function-to-function transformations. We evaluate NOIR across multiple 2D and 3D downstream tasks, including segmentation, shape completion, image-to-image translation, and image synthesis, on several public datasets such as Shenzhen, OASIS-4, SkullBreak, fastMRI, as well as an in-house clinical dataset. It achieves competitive performance at native resolution while demonstrating strong robustness to unseen discretizations, and empirically satisfies key theoretical properties of neural operators. The project page is available here: https://github.com/Sidaty1/NOIR-io.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

44 of 61 references.

References · 44

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  10. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  11. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  12. 2016HyperNetworkscited by 1,027
32 more
  1. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
  2. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 662
  3. 2021Neural Operator: Learning Maps Between Function Spacescited by 414
  4. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  5. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  6. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
  7. 2017Image reconstruction by domain transform manifold learningcited by 232
  8. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  9. 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 214
  10. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  11. 2017Deep Functional Maps: Structured Prediction for Dense Shape Correspondencecited by 134
  12. 2023Implicit Neural Representation in Medical Imaging: A Comparative Surveycited by 90
  13. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 88
  14. 2023Operator Learning with Neural Fields: Tackling PDEs on General Geometriescited by 84
  15. 2022COIN++: Neural Compression Across Modalitiescited by 82
  16. 2023Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learningcited by 57
  17. 2024WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesiscited by 56
  18. 2022textttGradICON: Approximate Diffeomorphisms via Gradient Inverse Consistencycited by 41
  19. 2023Point Cloud Diffusion Models for Automatic Implant Generationcited by 19
  20. 2024cWDM: Conditional Wavelet Diffusion Models for Cross-Modality 3D Medical Image Synthesiscited by 19
  21. 2019Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasoundcited by 12
  22. 2025Fit Pixels, Get Labels: Meta-learned Implicit Networks for Image Segmentationcited by 11
  23. 2024Classification, Regression and Segmentation directly from k-Space in Cardiac MRIcited by 8
  24. 2025fastWDM3D: Fast and Accurate 3D Healthy Tissue Inpaintingcited by 8
  25. 2022k-strip: A novel segmentation algorithm in k-space for the application of skull strippingcited by 7
  26. 2025MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fieldscited by 7
  27. 2023MRI Scan Synthesis Methods based on Clustering and Pix2Pixcited by 6
  28. 2023FNOSeg3D: Resolution-Robust 3D Image Segmentation with Fourier Neural Operatorcited by 3
  29. 2024Optimizing 3D Geometry Reconstruction from Implicit Neural Representationscited by 2
  30. 2025LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encodingcited by 2
  31. 2025Shape Completion and Real-Time Visualization in Robotic Ultrasound Spine Acquisitionscited by 2
  32. 2025cIDIR: Conditioned Implicit Neural Representation for Regularized Deformable Image Registrationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CATO: Charted Attention for Neural PDE Operatorscited by 0