mlsanityData to 14 Oct 2026

nerf2nerf: Pairwise Registration of Neural Radiance Fields

arXiv 2211.01600 ↗First posted 3 Nov 2022cs.CV cs.AI cs.ROcited by 39

Not on the map. Why?

Abstract (arXiv)

We introduce a technique for pairwise registration of neural fields that extends classical optimization-based local registration (i.e. ICP) to operate on Neural Radiance Fields (NeRF) -- neural 3D scene representations trained from collections of calibrated images. NeRF does not decompose illumination and color, so to make registration invariant to illumination, we introduce the concept of a ''surface field'' -- a field distilled from a pre-trained NeRF model that measures the likelihood of a point being on the surface of an object. We then cast nerf2nerf registration as a robust optimization that iteratively seeks a rigid transformation that aligns the surface fields of the two scenes. We evaluate the effectiveness of our technique by introducing a dataset of pre-trained NeRF scenes -- our synthetic scenes enable quantitative evaluations and comparisons to classical registration techniques, while our real scenes demonstrate the validity of our technique in real-world scenarios. Additional results available at: https://nerf2nerf.github.io

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 32 of its 67 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

32 of 67 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  6. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  7. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  8. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  9. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  10. 2021Neural Fields in Visual Computing and Beyondcited by 540
  11. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  12. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
20 more
  1. 2021Advances in Neural Renderingcited by 365
  2. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  3. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  4. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  5. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 233
  6. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  7. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  8. 2018The Perfect Match: 3D Point Cloud Matching with Smoothed Densitiescited by 169
  9. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  10. 2019NASA: Neural Articulated Shape Approximationcited by 149
  11. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  12. 20213D Neural Scene Representations for Visuomotor Controlcited by 111
  13. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  14. 2022NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fieldscited by 86
  15. 2017Guaranteed Outlier Removal for Point Cloud Registration with Correspondencescited by 62
  16. 2022Volume Rendering Digest (for NeRF)cited by 32
  17. 2020Tactile Object Pose Estimation from the First Touch with Geometric Contact Renderingcited by 20
  18. 2015PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalizationcited by 11
  19. 2019Linearized Multi-Sampling for Differentiable Image Transformationcited by 11
  20. 2017DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Modelcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 15; 2024: 13; 2025: 8; 2026: 2.

39 papers.

Sort:

By area:

  1. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 113
  2. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
  3. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  4. 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
  5. 2023Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projectioncited by 36
  6. 2023DReg-NeRF: Deep Registration for Neural Radiance Fieldscited by 21
  7. 2024GaussReg: Fast 3D Registration with Gaussian Splattingcited by 19
  8. 2023SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fieldscited by 13
  9. 2023NEAT: Distilling 3D Wireframes from Neural Attraction Fieldscited by 12
  10. 2023GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Cloudscited by 11
  11. 2023Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use casescited by 10
  12. 2024BANF: Band-limited Neural Fields for Levels of Detail Reconstructioncited by 10
27 more
  1. 2024ZeroGS: Training 3D Gaussian Splatting from Unposed Imagescited by 10
  2. 2023Volumetric Rendering with Baked Quadrature Fieldscited by 9
  3. 2024Evaluating Alternatives to SFM Point Cloud Initialization for Gaussian Splattingcited by 9
  4. 2023Canonical Factors for Hybrid Neural Fieldscited by 8
  5. 2025SIREN: Semantic, Initialization-Free Registration of Multi-Robot Gaussian Splatting Mapscited by 7
  6. 2023Clean-NeRF: Reformulating NeRF to account for View-Dependent Observationscited by 6
  7. 2023C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRFcited by 6
  8. 2024Blending Distributed NeRFs with Tri-stage Robust Pose Optimizationcited by 6
  9. 2023NeRFuser: Large-Scale Scene Representation by NeRF Fusioncited by 5
  10. 2024PhotoReg: Photometrically Registering 3D Gaussian Splatting Modelscited by 5
  11. 2025Scalable and High-Quality Neural Implicit Representation for 3D Reconstructioncited by 5
  12. 2023TEGLO: High Fidelity Canonical Texture Mapping from Single-View Imagescited by 4
  13. 2023SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstructioncited by 4
  14. 2024Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fieldscited by 4
  15. 2025Learning 3D Scene Analogies with Neural Contextual Scene Mapscited by 4
  16. 2025Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splattingcited by 4
  17. 2025Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Featurescited by 3
  18. 2023Registering Neural Radiance Fields as 3D Density Imagescited by 2
  19. 2023MARF: The Medial Atom Ray Field Object Representationcited by 2
  20. 2024Fit-NGP: Fitting Object Models to Neural Graphics Primitivescited by 2
  21. 2024Registering Neural 4D Gaussians for Endoscopic Surgerycited by 2
  22. 2025Multi-View Foundation Modelscited by 2
  23. 2024VF-NeRF: Viewshed Fields for Rigid NeRF Registrationcited by 1
  24. 2025Metropolis-Hastings Sampling for 3D Gaussian Reconstructioncited by 1
  25. 2026Scene Grounding In the Wildcited by 1
  26. 2026GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Secondscited by 1
  27. 2025Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoningcited by 0