mlsanityData to 14 Oct 2026

DReg-NeRF: Deep Registration for Neural Radiance Fields

arXiv 2308.09386 ↗First posted 18 Aug 2023cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Although Neural Radiance Fields (NeRF) is popular in the computer vision community recently, registering multiple NeRFs has yet to gain much attention. Unlike the existing work, NeRF2NeRF, which is based on traditional optimization methods and needs human annotated keypoints, we propose DReg-NeRF to solve the NeRF registration problem on object-centric scenes without human intervention. After training NeRF models, our DReg-NeRF first extracts features from the occupancy grid in NeRF. Subsequently, our DReg-NeRF utilizes a transformer architecture with self-attention and cross-attention layers to learn the relations between pairwise NeRF blocks. In contrast to state-of-the-art (SOTA) point cloud registration methods, the decoupled correspondences are supervised by surface fields without any ground truth overlapping labels. We construct a novel view synthesis dataset with 1,700+ 3D objects obtained from Objaverse to train our network. When evaluated on the test set, our proposed method beats the SOTA point cloud registration methods by a large margin, with a mean RPE=9.67circ and a mean RTE=0.038. Our code is available at https://github.com/AIBluefisher/DReg-NeRF.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 36 of its 47 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

36 of 47 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  8. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  9. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  10. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  12. 2020Neural Sparse Voxel Fieldscited by 959
24 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  3. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  4. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  5. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 398
  6. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  7. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  8. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  9. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  10. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  11. 2017A General and Adaptive Robust Loss Functioncited by 236
  12. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  13. 2023RobustNeRF: Ignoring Distractors with Robust Lossescited by 101
  14. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 96
  15. 2022NerfAcc: A General NeRF Acceleration Toolboxcited by 74
  16. 2023Segment Anything in 3D with Radiance Fieldscited by 62
  17. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  18. 2022nerf2nerf: Pairwise Registration of Neural Radiance Fieldscited by 39
  19. 2022Volume Rendering Digest (for NeRF)cited by 32
  20. 2018Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoodscited by 21
  21. 2019Graph-Based Parallel Large Scale Structure from Motioncited by 21
  22. 2021Hybrid Rotation Averaging: A Fast and Robust Rotation Averaging Approachcited by 19
  23. 2022Zero NeRF: Registration with Zero Overlapcited by 7
  24. 2023AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 12; 2025: 3; 2026: 3.

21 papers.

Sort:

  1. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 60
  2. 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
  3. 2024GaussReg: Fast 3D Registration with Gaussian Splattingcited by 19
  4. 2024TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Trackscited by 12
  5. 2024ZeroGS: Training 3D Gaussian Splatting from Unposed Imagescited by 10
  6. 2024NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fieldscited by 9
  7. 2023Radar Fields: An Extension of Radiance Fields to SARcited by 7
  8. 2025SIREN: Semantic, Initialization-Free Registration of Multi-Robot Gaussian Splatting Mapscited by 7
  9. 2023C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRFcited by 6
  10. 2024Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenescited by 6
  11. 2024PhotoReg: Photometrically Registering 3D Gaussian Splatting Modelscited by 5
  12. 2023SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstructioncited by 4
9 more
  1. 2024Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fieldscited by 4
  2. 2025Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splattingcited by 4
  3. 2025Automated 3D-GS Registration and Fusion via Skeleton Alignment and Gaussian-Adaptive Featurescited by 3
  4. 2024Registering Neural 4D Gaussians for Endoscopic Surgerycited by 2
  5. 2024VF-NeRF: Viewshed Fields for Rigid NeRF Registrationcited by 1
  6. 2024FBINeRF: Feature-Based Integrated Recurrent Network for Pinhole and Fisheye Neural Radiance Fieldscited by 1
  7. 2026GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Secondscited by 1
  8. 2026Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignmentcited by 0
  9. 2026GeGS-PCR: Effective and Robust 3D Point Cloud Registration with Two-Stage Color-Enhanced Geometric-3DGS Fusioncited by 0