# Registering Neural Radiance Fields as 3D Density Images

arXiv: https://arxiv.org/abs/2305.12843 · HTML: https://mlsanity.com/paper/2305.12843/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 56 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs](https://mlsanity.com/paper/2112.10703/) (2021)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation](https://mlsanity.com/paper/2112.05124/) (2021)
- [Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector](https://mlsanity.com/paper/1908.01998/) (2019)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://mlsanity.com/paper/1808.10322/) (2018)
- [3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration](https://mlsanity.com/paper/1807.09413/) (2018)
- [Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2211.11505/) (2022)
- [NeRF-RPN: A general framework for object detection in NeRFs](https://mlsanity.com/paper/2211.11646/) (2022)
- [Local Descriptors Optimized for Average Precision](https://mlsanity.com/paper/1804.05312/) (2018)
- [nerf2nerf: Pairwise Registration of Neural Radiance Fields](https://mlsanity.com/paper/2211.01600/) (2022)
- [Learning Spread-out Local Feature Descriptors](https://mlsanity.com/paper/1708.06320/) (2017)
- [Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT](https://mlsanity.com/paper/1405.5769/) (2014)
- [Zero NeRF: Registration with Zero Overlap](https://mlsanity.com/paper/2211.12544/) (2022)

## Built on by (most cited first, 2 of 2)

- [SIREN: Semantic, Initialization-Free Registration of Multi-Robot Gaussian Splatting Maps](https://mlsanity.com/paper/2502.06519/) (2025)
- [Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning](https://mlsanity.com/paper/2509.00465/) (2025)

## Abstract (arXiv)

No significant work has been done to directly merge two partially overlapping scenes using NeRF representations. Given pre-trained NeRF models of a 3D scene with partial overlapping, this paper aligns them with a rigid transform, by generalizing the traditional registration pipeline, that is, key point detection and point set registration, to operate on 3D density fields. To describe corner points as key points in 3D, we propose to use universal pre-trained descriptor-generating neural networks that can be trained and tested on different scenes. We perform experiments to demonstrate that the descriptor networks can be conveniently trained using a contrastive learning strategy. We demonstrate that our method, as a global approach, can effectively register NeRF models, thus making possible future large-scale NeRF construction by registering its smaller and overlapping NeRFs captured individually.