NoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prior

Simple item page
dc.contributor.authorShi, Dongboen_US
dc.contributor.authorCao, Shenen_US
dc.contributor.authorWu, Bojianen_US
dc.contributor.authorGuo, Jinhuien_US
dc.contributor.authorFan, Lubinen_US
dc.contributor.authorChen, Renjieen_US
dc.contributor.authorLiu, Ligangen_US
dc.contributor.authorYe, Jiepingen_US
dc.contributor.editorBousseau, Adrienen_US
dc.contributor.editorDay, Angelaen_US
dc.date.accessioned2025-05-09T09:09:51Z
dc.date.available2025-05-09T09:09:51Z
dc.date.issued2025
dc.description.abstractIn this paper, we introduce NoPe-NeRF++, a novel local-to-global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods, particularly NoPe-NeRF, which focus solely on the local relationships within images, often struggle to recover accurate camera poses in complex scenarios. To overcome the challenges, our approach begins with a relative pose initialization with explicit feature matching, followed by a local joint optimization to enhance the pose estimation for training a more robust NeRF representation. This method significantly improves the quality of initial poses. Additionally, we introduce global optimization phase that incorporates geometric consistency constraints through bundle adjustment, which integrates feature trajectories to further refine poses and collectively boost the quality of NeRF. Notably, our method is the first work that seamlessly combines the local and global cues with NeRF, and outperforms state-of-the-art methods in both pose estimation accuracy and novel view synthesis. Extensive evaluations on benchmark datasets demonstrate our superior performance and robustness, even in challenging scenes, thus validating our design choices.en_US
dc.description.number2
dc.description.sectionheadersSplat-tacular Radiance Fields
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70012
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70012
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70012
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution-NonCommercial 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image-based rendering
dc.subjectComputing methodologies → Image
dc.subjectbased rendering
dc.titleNoPe-NeRF++: Local-to-Global Optimization of NeRF with No Pose Prioren_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70012.pdf
Size:
46.84 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Full Papers - CGF 44-Issue 2
44-Issue 2