ROI-NeRFs: Hi-Fi Visualization of Objects of Interest within a Scene by NeRFs Composition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913695992381440 |
|---|---|
| author | Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone |
| author_facet | Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone |
| contents | Efficient and accurate 3D reconstruction is essential for applications in cultural heritage. This study addresses the challenge of visualizing objects within large-scale scenes at a high level of detail (LOD) using Neural Radiance Fields (NeRFs). The aim is to improve the visual fidelity of chosen objects while maintaining the efficiency of the computations by focusing on details only for relevant content. The proposed ROI-NeRFs framework divides the scene into a Scene NeRF, which represents the overall scene at moderate detail, and multiple ROI NeRFs that focus on user-defined objects of interest. An object-focused camera selection module automatically groups relevant cameras for each NeRF training during the decomposition phase. In the composition phase, a Ray-level Compositional Rendering technique combines information from the Scene NeRF and ROI NeRFs, allowing simultaneous multi-object rendering composition. Quantitative and qualitative experiments conducted on two real-world datasets, including one on a complex eighteen's century cultural heritage room, demonstrate superior performance compared to baseline methods, improving LOD for object regions, minimizing artifacts, and without significantly increasing inference time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ROI-NeRFs: Hi-Fi Visualization of Objects of Interest within a Scene by NeRFs Composition Bui, Quoc-Anh Rougeron, Gilles Morin, Géraldine Gasparini, Simone Computer Vision and Pattern Recognition Graphics 68U05, 68T45 (Primary) 68T07, 68-04 (Secondary) I.2.10; I.3.3; I.3.5; I.3.7; I.4.5; I.4.6; I.4.8; I.4.10 Efficient and accurate 3D reconstruction is essential for applications in cultural heritage. This study addresses the challenge of visualizing objects within large-scale scenes at a high level of detail (LOD) using Neural Radiance Fields (NeRFs). The aim is to improve the visual fidelity of chosen objects while maintaining the efficiency of the computations by focusing on details only for relevant content. The proposed ROI-NeRFs framework divides the scene into a Scene NeRF, which represents the overall scene at moderate detail, and multiple ROI NeRFs that focus on user-defined objects of interest. An object-focused camera selection module automatically groups relevant cameras for each NeRF training during the decomposition phase. In the composition phase, a Ray-level Compositional Rendering technique combines information from the Scene NeRF and ROI NeRFs, allowing simultaneous multi-object rendering composition. Quantitative and qualitative experiments conducted on two real-world datasets, including one on a complex eighteen's century cultural heritage room, demonstrate superior performance compared to baseline methods, improving LOD for object regions, minimizing artifacts, and without significantly increasing inference time. |
| title | ROI-NeRFs: Hi-Fi Visualization of Objects of Interest within a Scene by NeRFs Composition |
| topic | Computer Vision and Pattern Recognition Graphics 68U05, 68T45 (Primary) 68T07, 68-04 (Secondary) I.2.10; I.3.3; I.3.5; I.3.7; I.4.5; I.4.6; I.4.8; I.4.10 |
| url | https://arxiv.org/abs/2502.12673 |