mlsanityData to 7 Oct 2026

Accelerating Neural Field Training via Soft Mining

arXiv 2312.00075 ↗First posted 29 Nov 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

We present an approach to accelerate Neural Field training by efficiently selecting sampling locations. While Neural Fields have recently become popular, it is often trained by uniformly sampling the training domain, or through handcrafted heuristics. We show that improved convergence and final training quality can be achieved by a soft mining technique based on importance sampling: rather than either considering or ignoring a pixel completely, we weigh the corresponding loss by a scalar. To implement our idea we use Langevin Monte-Carlo sampling. We show that by doing so, regions with higher error are being selected more frequently, leading to more than 2x improvement in convergence speed. The code and related resources for this study are publicly available at https://ubc-vision.github.io/nf-soft-mining/.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 29 Nov 2023.

Builds on

36 of 51 references.

References · 36

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  12. 2020Neural Sparse Voxel Fieldscited by 959
24 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  6. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  7. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  8. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  9. 2021Neural Fields in Visual Computing and Beyondcited by 539
  10. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  11. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 470
  12. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  13. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  14. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  15. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 142
  16. 2021Light Field Neural Renderingcited by 108
  17. 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
  18. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
  19. 2016Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreaucited by 83
  20. 2018The promises and pitfalls of Stochastic Gradient Langevin Dynamicscited by 56
  21. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  22. 2022Neural Fourier Filter Bankcited by 29
  23. 2020VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learningcited by 25
  24. 2018Deep Metric Learning by Online Soft Mining and Class-Aware Attentioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 7; 2026: 3.

13 papers.

Sort:

  1. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
  2. 2025Optimizing Rank for High-Fidelity Implicit Neural Representationscited by 7
  3. 2025MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fieldscited by 6
  4. 2024Expansive Supervision for Neural Radiance Fieldcited by 5
  5. 2024EVOS: Efficient Implicit Neural Training via EVOlutionary Selectorcited by 5
  6. 2025Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstructioncited by 4
  7. 2025NTK-Guided Implicit Neural Teachingcited by 2
  8. 2025Multiple Instance Learning Framework with Masked Hard Instance Mining for Gigapixel Histopathology Image Analysiscited by 1
  9. 2025TabINR: An Implicit Neural Representation Framework for Tabular Data Imputationcited by 1
  10. 2025MCBlock: Boosting Neural Radiance Field Training Speed by MCTS-based Dynamic-Resolution Ray Samplingcited by 0
  11. 2026TurboGS: Accelerating 3D Gaussian Splatting via Error-Guided Sparse Pixel Sampling and Optimizationcited by 0
  12. 2026InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Samplingcited by 0
1 more
  1. 2026Resolution-Flexible Decoding for Hybrid Neural Video Representationscited by 0