mlsanityData to 7 Oct 2026

Neural Experts: Mixture of Experts for Implicit Neural Representations

arXiv 2410.21643 ↗First posted 29 Oct 2024cs.CVcited by 9

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a single network for the entire domain, imposing many global constraints on a single function. In this paper, we propose a mixture of experts (MoE) implicit neural representation approach that enables learning local piece-wise continuous functions that simultaneously learns to subdivide the domain and fit locally. We show that incorporating a mixture of experts architecture into existing INR formulations provides a boost in speed, accuracy, and memory requirements. Additionally, we introduce novel conditioning and pretraining methods for the gating network that improves convergence to the desired solution. We evaluate the effectiveness of our approach on multiple reconstruction tasks, including surface reconstruction, image reconstruction, and audio signal reconstruction and show improved performance compared to non-MoE methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 35 of its 49 references that are in the map. First posted on arXiv 29 Oct 2024.

Builds on

35 of 49 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MoEC: Mixture of Experts Implicit Neural Compression3 Dec

Other references · 34

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Segment Anythingcited by 8,158
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  11. 2024Mixtral of Expertscited by 1,785
  12. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
22 more
  1. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 890
  2. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  5. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  6. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  7. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  8. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  9. 2020State of the Art on Neural Renderingcited by 276
  10. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  11. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  12. 2020DeRF: Decomposed Radiance Fieldscited by 163
  13. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  14. 2021Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPscited by 134
  15. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  16. 2023FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functionscited by 77
  17. 2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 76
  18. 2021Geometry-Consistent Neural Shape Representation with Implicit Displacement Fieldscited by 60
  19. 2018Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networkscited by 44
  20. 2015Generative Image Modeling Using Spatial LSTMscited by 35
  21. 2024A Sampling Theory Perspective on Activations for Implicit Neural Representationscited by 23
  22. 2023Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesiscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Continuous Representation Methods, Theories, and Applications: An Overview and Perspectivescited by 4
  2. 2025SASNet: Spatially-Adaptive Sinusoidal Networks for INRscited by 3
  3. 2025FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonalitycited by 2
  4. 2025FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensemblescited by 1
  5. 2025Soft Task-Aware Routing of Experts for Equivariant Representation Learningcited by 0
  6. 2025Dynamical Implicit Neural Representationscited by 0
  7. 2026MME: Mixture of Mesh Experts with Random Walk Transformer Gatingcited by 0
  8. 2026MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI Reconstructioncited by 0
  9. 2026From Scalars to Time Series: Rethinking Implicit Neural Representations for Time-Varying Volumetric Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Neural Implicit Dictionary via Mixture-of-Expert Training
  2. 2026Weight-Space Mixture-of-Experts for Implicit Neural Representation Classification
  3. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  4. 2025Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks
  5. 2026MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI Reconstruction
  6. 2026Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
  7. 2020Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
  8. 2026Mixture of Experts with Soft Nearest Neighbor Loss: Resolving Expert Collapse via Representation Disentanglement