GS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lighting

Simple item page
dc.contributor.authorLi, Jiazeen_US
dc.contributor.authorWen, Zhengyuen_US
dc.contributor.authorZhang, Luoen_US
dc.contributor.authorHu, Jiangbeien_US
dc.contributor.authorHou, Feien_US
dc.contributor.authorZhang, Zhebinen_US
dc.contributor.authorHe, Yingen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:07:05Z
dc.date.available2024-10-13T18:07:05Z
dc.date.issued2024
dc.description.abstractThe 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi-view images, enabling real-time rendering. While point-based rasterization effectively reduces computational demands for rendering, it often struggles to accurately reconstruct the geometry of the target object, especially under strong lighting conditions. Strong lighting can cause significant color variations on the object's surface when viewed from different directions, complicating the reconstruction process. To address this challenge, we introduce an approach that combines octree-based implicit surface representations with Gaussian Splatting. Initially, it reconstructs a signed distance field (SDF) and a radiance field through volume rendering, encoding them in a low-resolution octree. This initial SDF represents the coarse geometry of the target object. Subsequently, it introduces 3D Gaussians as additional degrees of freedom, which are guided by the initial SDF. In the third stage, the optimized Gaussians enhance the accuracy of the SDF, enabling the recovery of finer geometric details compared to the initial SDF. Finally, the refined SDF is used to further optimize the 3D Gaussians via splatting, eliminating those that contribute little to the visual appearance. Experimental results show that our method, which leverages the distribution of 3D Gaussians with SDFs, reconstructs more accurate geometry, particularly in images with specular highlights caused by strong lighting. The source code can be downloaded from https://github.com/LaoChui999/GS-Octree.en_US
dc.description.number7
dc.description.sectionheaders3D Reconstruction and Novel View Synthesis I
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15206
dc.identifier.issn1467-8659
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15206
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15206
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image-based rendering; Volumetric models; Rendering; Shape representations
dc.subjectComputing methodologies → Image
dc.subjectbased rendering
dc.subjectVolumetric models
dc.subjectRendering
dc.subjectShape representations
dc.titleGS-Octree: Octree-based 3D Gaussian Splatting for Robust Object-level 3D Reconstruction Under Strong Lightingen_US
Files
Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
cgf15206.pdf
Size:
61.54 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
paper1282_mm.pdf
Size:
25.84 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 7