OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields
In situations with a limited number of posed images, choosing the most suitable viewpoints becomes crucial for accurate Neural Radiance Fields (NeRF) modeling. Current approaches for view selection often rely on heuristic methods or are computationally intensive. To address these challenges, we intr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843224006642 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850189969884184576 |
|---|---|
| author | You Li Rui Li Ziwei Li Renzhong Guo Shengjun Tang |
| author_facet | You Li Rui Li Ziwei Li Renzhong Guo Shengjun Tang |
| author_sort | You Li |
| collection | DOAJ |
| description | In situations with a limited number of posed images, choosing the most suitable viewpoints becomes crucial for accurate Neural Radiance Fields (NeRF) modeling. Current approaches for view selection often rely on heuristic methods or are computationally intensive. To address these challenges, we introduce a new framework, OptiViewNeRF, which leverages scene uncertainty to guide the view selection process. Initially, an uncertainty estimation model of the entire scene is developed based on a preliminary NeRF model. This model then informs the selection of new perception viewpoints using a batch view selection strategy, allowing the entire process to be completed in a single iteration. By selecting viewpoints that provide informative data, this approach improves novel view synthesis results and accurately reconstructs 3D scenes. Experimental results on two selected datasets show that the proposed method effectively identifies informative viewpoints, resulting in more accurate scene reconstructions compared to baseline and state-of-the-art methods. |
| format | Article |
| id | doaj-art-3e73ad3cc4a548f8a656efe54c0e1817 |
| institution | OA Journals |
| issn | 1569-8432 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj-art-3e73ad3cc4a548f8a656efe54c0e18172025-08-20T02:15:28ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322025-02-0113610430610.1016/j.jag.2024.104306OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance FieldsYou Li0Rui Li1Ziwei Li2Renzhong Guo3Shengjun Tang4Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, PR China; Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, PR ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, PR China; Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, PR ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, PR China; Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, PR ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, PR China; Research Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, PR ChinaResearch Institute for Smart Cities, School of Architecture and Urban Planning, Shenzhen University, Shenzhen, PR China; Corresponding author.In situations with a limited number of posed images, choosing the most suitable viewpoints becomes crucial for accurate Neural Radiance Fields (NeRF) modeling. Current approaches for view selection often rely on heuristic methods or are computationally intensive. To address these challenges, we introduce a new framework, OptiViewNeRF, which leverages scene uncertainty to guide the view selection process. Initially, an uncertainty estimation model of the entire scene is developed based on a preliminary NeRF model. This model then informs the selection of new perception viewpoints using a batch view selection strategy, allowing the entire process to be completed in a single iteration. By selecting viewpoints that provide informative data, this approach improves novel view synthesis results and accurately reconstructs 3D scenes. Experimental results on two selected datasets show that the proposed method effectively identifies informative viewpoints, resulting in more accurate scene reconstructions compared to baseline and state-of-the-art methods.http://www.sciencedirect.com/science/article/pii/S15698432240066423D reconstructionNeRFUncertaintyView selectionUAV data |
| spellingShingle | You Li Rui Li Ziwei Li Renzhong Guo Shengjun Tang OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields International Journal of Applied Earth Observations and Geoinformation 3D reconstruction NeRF Uncertainty View selection UAV data |
| title | OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields |
| title_full | OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields |
| title_fullStr | OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields |
| title_full_unstemmed | OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields |
| title_short | OptiViewNeRF: Optimizing 3D reconstruction via batch view selection and scene uncertainty in Neural Radiance Fields |
| title_sort | optiviewnerf optimizing 3d reconstruction via batch view selection and scene uncertainty in neural radiance fields |
| topic | 3D reconstruction NeRF Uncertainty View selection UAV data |
| url | http://www.sciencedirect.com/science/article/pii/S1569843224006642 |
| work_keys_str_mv | AT youli optiviewnerfoptimizing3dreconstructionviabatchviewselectionandsceneuncertaintyinneuralradiancefields AT ruili optiviewnerfoptimizing3dreconstructionviabatchviewselectionandsceneuncertaintyinneuralradiancefields AT ziweili optiviewnerfoptimizing3dreconstructionviabatchviewselectionandsceneuncertaintyinneuralradiancefields AT renzhongguo optiviewnerfoptimizing3dreconstructionviabatchviewselectionandsceneuncertaintyinneuralradiancefields AT shengjuntang optiviewnerfoptimizing3dreconstructionviabatchviewselectionandsceneuncertaintyinneuralradiancefields |