Self-Calibrating Fisheye Lens Aberrations for Novel View Synthesis

Simple item page
dc.contributor.authorXiang, Jinhuien_US
dc.contributor.authorLi, Yuqien_US
dc.contributor.authorLi, Jiabaoen_US
dc.contributor.authorZheng, Wenxingen_US
dc.contributor.authorFu, Qiangen_US
dc.contributor.editorWimmer, Michaelen_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWestermann, RĂĽdigeren_US
dc.date.accessioned2025-11-07T08:33:00Z
dc.date.available2025-11-07T08:33:00Z
dc.date.issued2025
dc.description.abstractNeural rendering techniques, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D-GS), have led to significant advancements in scene reconstruction and novel view synthesis (NVS). These methods assume the use of an ideal pinhole model, which is free from lens distortion and optical aberrations. However, fisheye lenses introduce unavoidable aberrations due to their wide-angle design and complex manufacturing, leading to multi-view inconsistencies that compromise scene reconstruction quality. In this paper, we propose an end-to-end framework that integrates a standard 3D reconstruction pipeline with our lens aberration model to simultaneously calibrate lens aberrations and reconstruct 3D scenes. By modelling the real imaging process and jointly optimising both tasks, our framework eliminates the impact of aberration-induced inconsistencies on reconstruction. Additionally, we propose a curriculum learning approach that ensures stable optimisation and high-quality reconstruction results, even in the presence of multiple aberrations. To address the limitations of existing benchmarks, we introduce AbeRec, a dataset composed of scenes captured with lenses exhibiting severe aberrations. Extensive experiments on both existing public datasets and our proposed dataset demonstrate that our method not only significantly outperforms previous state-of-the-art methods on fisheye lenses with severe aberrations but also generalises well to scenes captured by non-fisheye lenses. Code and datasets are available at https://github.com/CPREgroup/Calibrating-Fisheye-Lens-Aberration-for-NVS.en_US
dc.description.number6
dc.description.sectionheadersOriginal Article
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70148
dc.identifier.issn1467-8659
dc.identifier.pages16 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70148
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70148
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subject3D reconstruction
dc.subjectlens aberration calibration
dc.subjectnovel view synthesis
dc.subjectComputing methodologies→Reconstruction
dc.subjectRendering
dc.subjectCamera calibration
dc.subjectComputational photography
dc.titleSelf-Calibrating Fisheye Lens Aberrations for Novel View Synthesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
06_cgf70148.pdf
Size:
7.67 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 6