Communication Dans Un Congrès Année : 2025

Online 3D Scene Reconstruction Using Neural Object Priors

Résumé

This paper addresses the problem of reconstructing a scene online at the level of objects given an RGB-D video sequence. While current object-aware neural implicit representations hold promise, they are limited in online reconstruction efficiency and shape completion. Our main contributions to alleviate the above limitations are twofold. First, we propose a feature grid interpolation mechanism to continuously update grid-based object-centric neural implicit representations as new object parts are revealed. Second, we construct an object library with previously mapped objects in advance and leverage the corresponding shape priors to initialize geometric object models in new videos, subsequently completing them with novel views as well as synthesized past views to avoid losing original object details. Extensive experiments on synthetic environments from the Replica dataset, real-world ScanNet sequences and videos captured in our laboratory demonstrate that our approach outperforms state-of-the-art neural implicit models for this task in terms of reconstruction accuracy and completeness.
Fichier principal
Vignette du fichier
3DV_2025_Online_Scene_Reconstruction-CameraReady.pdf (24.52 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04888719 , version 1 (15-01-2025)

Licence

Identifiants

  • HAL Id : hal-04888719 , version 1

Citer

Thomas Chabal, Shizhe Chen, Jean Ponce, Cordelia Schmid. Online 3D Scene Reconstruction Using Neural Object Priors. 3DV 2025 - 12th International Conference on 3D Vision 2025, Mar 2025, Singapore, Singapore. ⟨hal-04888719⟩
0 Consultations
0 Téléchargements

Partager

More