PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 13, 2025Computer Graphics Forum2 citations

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

View Full Paper
YYYixin YangYZYang ZhouHHHui Huang

Key Points

  • The method finds significant improvements in reconstruction quality, particularly for glossy surfaces.
  • Using a novel depth convergence loss, it emphasizes depth continuity across various data sets.
  • Evaluations show that this method surpasses traditional 2D Gaussian Splatting, addressing reflection discontinuities.
  • Overall, the approach rectifies depth criteria to deliver more complete and accurate surface representations.

Abstract

Abstract Recently, 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/UnbiasedSurfel.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Yang et al. (2025) studied this question.

synapsesocial.com/papers/68ec51e642911f61ef8b249fhttps://doi.org/10.1111/cgf.70252
Ask AI
Helpful
Bookmark
Share
View Full Paper