Introducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstruction

Simple item page
dc.contributor.authorYang, Yixinen_US
dc.contributor.authorZhou, Yangen_US
dc.contributor.authorHuang, Huien_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:02:32Z
dc.date.available2025-10-07T05:02:32Z
dc.date.issued2025
dc.description.abstractRecently, 2D Gaussian Splatting (2DGS) has demonstrated superior geometry reconstruction quality than the popular 3DGS by using 2D surfels to approximate thin surfaces. However, it falls short when dealing with glossy surfaces, resulting in visible holes in these areas. We find that the reflection discontinuity causes the issue. To fit the jump from diffuse to specular reflection at different viewing angles, depth bias is introduced in the optimized Gaussian primitives. To address that, we first replace the depth distortion loss in 2DGS with a novel depth convergence loss, which imposes a strong constraint on depth continuity. Then, we rectify the depth criterion in determining the actual surface, which fully accounts for all the intersecting Gaussians along the ray. Qualitative and quantitative evaluations across various datasets reveal that our method significantly improves reconstruction quality, with more complete and accurate surfaces than 2DGS. Code is available at https://github.com/ XiaoXinyyx/Unbiased_Surfel.en_US
dc.description.number7
dc.description.sectionheadersGaussian Splatting
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70252
dc.identifier.issn1467-8659
dc.identifier.pages9 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70252
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70252
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Rendering; Machine learning approaches; Shape modeling
dc.subjectComputing methodologies → Rendering
dc.subjectMachine learning approaches
dc.subjectShape modeling
dc.titleIntroducing Unbiased Depth into 2D Gaussian Splatting for High-accuracy Surface Reconstructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70252.pdf
Size:
16.53 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7