# DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images

arXiv: https://arxiv.org/abs/2403.13199 · HTML: https://mlsanity.com/paper/2403.13199/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 19 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [Federated Learning with Buffered Asynchronous Aggregation](https://mlsanity.com/paper/2106.06639/) (2021)
- [Hallucinated Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2111.15246/) (2021)
- [Gradient Inversion with Generative Image Prior](https://mlsanity.com/paper/2110.14962/) (2021)
- [Revealing Scenes by Inverting Structure from Motion Reconstructions](https://mlsanity.com/paper/1904.03303/) (2019)
- [Removing Objects From Neural Radiance Fields](https://mlsanity.com/paper/2212.11966/) (2022)
- [LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning](https://mlsanity.com/paper/2109.14236/) (2021)
- [Crowdsampling the Plenoptic Function](https://mlsanity.com/paper/2007.15194/) (2020)
- [Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collections](https://mlsanity.com/paper/2307.08093/) (2023)
- [Real-Time Neural Light Field on Mobile Devices](https://mlsanity.com/paper/2212.08057/) (2022)
- [NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning](https://mlsanity.com/paper/2112.12785/) (2021)
- [Communication-Computation Efficient Secure Aggregation for Federated Learning](https://mlsanity.com/paper/2012.05433/) (2020)
- [Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields](https://mlsanity.com/paper/2309.06030/) (2023)
- [Federated Neural Radiance Fields](https://mlsanity.com/paper/2305.01163/) (2023)
- [Di-NeRF: Distributed NeRF for Collaborative Learning with Relative Pose Refinement](https://mlsanity.com/paper/2402.01485/) (2024)

## Built on by (most cited first, 4 of 4)

- [LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents](https://mlsanity.com/paper/2512.17445/) (2025)
- [FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields](https://mlsanity.com/paper/2508.06301/) (2025)
- [Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF](https://mlsanity.com/paper/2508.00967/) (2025)
- [Tiny-DroNeRF: Tiny Neural Radiance Fields aboard Federated Learning-enabled Nano-drones](https://mlsanity.com/paper/2603.01850/) (2026)

## Abstract (arXiv)

Neural radiance fields (NeRFs) show potential for transforming images captured worldwide into immersive 3D visual experiences. However, most of this captured visual data remains siloed in our camera rolls as these images contain personal details. Even if made public, the problem of learning 3D representations of billions of scenes captured daily in a centralized manner is computationally intractable. Our approach, DecentNeRF, is the first attempt at decentralized, crowd-sourced NeRFs that require ~ 104× less server computing for a scene than a centralized approach. Instead of sending the raw data, our approach requires users to send a 3D representation, distributing the high computation cost of training centralized NeRFs between the users. It learns photorealistic scene representations by decomposing users' 3D views into personal and global NeRFs and a novel optimally weighted aggregation of only the latter. We validate the advantage of our approach to learn NeRFs with photorealism and minimal server computation cost on structured synthetic and real-world photo tourism datasets. We further analyze how secure aggregation of global NeRFs in DecentNeRF minimizes the undesired reconstruction of personal content by the server.