mlsanityData to 7 Oct 2026

DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images

arXiv 2403.13199 ↗First posted 19 Mar 2024cs.CV cs.DCcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 19 Mar 2024.

Builds on

24 of 34 references.

References · 24

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2015Fast R-CNNcited by 2,930
  4. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  5. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  6. 2018How To Backdoor Federated Learningcited by 745
  7. 2021Towards Personalized Federated Learningcited by 462
  8. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  10. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  11. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  12. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
12 more
  1. 2021Gradient Inversion with Generative Image Priorcited by 101
  2. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  3. 2022Removing Objects From Neural Radiance Fieldscited by 66
  4. 2021LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learningcited by 63
  5. 2020Crowdsampling the Plenoptic Functioncited by 62
  6. 2023Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collectionscited by 54
  7. 2022Real-Time Neural Light Field on Mobile Devicescited by 48
  8. 2021NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learningcited by 21
  9. 2020Communication-Computation Efficient Secure Aggregation for Federated Learningcited by 18
  10. 2023Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fieldscited by 8
  11. 2023Federated Neural Radiance Fieldscited by 4
  12. 2024Di-NeRF: Distributed NeRF for Collaborative Learning with Relative Pose Refinementcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agentscited by 3
  2. 2025FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fieldscited by 1
  3. 2025Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRFcited by 0
  4. 2026Tiny-DroNeRF: Tiny Neural Radiance Fields aboard Federated Learning-enabled Nano-dronescited by 0