Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning

arXiv:2403.11460v1 Announce Type: new
Abstract: In this work, we present Fed3DGS, a scalable 3D reconstruction framework based on 3D Gaussian splatting (3DGS) with federated learning. Existing city-scale reconstruction methods typically adopt a centralized approach, which gathers all data in a central server and reconstructs scenes. The approach hampers scalability because it places a heavy load on the server and demands extensive data storage when reconstructing scenes on a scale beyond city-scale. In pursuit of a more scalable 3D reconstruction, we …

3d reconstruction abstract arxiv city cs.cv data federated learning framework scalability scalable scale server type work